The Magical Black Box

Google's mission statement is "organize the world's information and make it universally accessible and useful."

That mission is so profound & so important the associated court documents in their antitrust cases must be withheld from public consumption.

Before document sharing was disallowed, some were shared publicly.

Internal emails stated:

  • Hal Varian was off in his public interviews where he suggested it was the algorithms rather than the amount of data which is prime driver of relevancy.
  • Apple would not get any revshare if there was a user choice screen & must set Google as the default search engine to qualify for any revshare.
  • Google has a policy of being vague about using clickstream data to influence ranking, though they have heavily relied upon clickstream data to influence ranking. Advances in machine learning have made it easier to score content to where the clickstream data had become less important.
  • When Apple Maps launched & Google Maps lost the default position on iOS Google Maps lost 60% of their iOS distribution, and that was with how poorly the Apple Maps roll out went.
  • Google sometimes subverted their typical auction dynamics and would flip the order of the top 2 ads to boost ad revenues.
  • Google had a policy of "shaking the cushions" to hit the quarterly numbers by changing advertiser ad prices without informing advertisers that they'd be competing in a rigged auction with artificially manipulated shill bids from the auctioneer competing against them.

When Google talked about hitting the quarterly numbers with shaking the cusions the 5% number which was shared skewed a bit low:

For a brand campaign focused on a niche product, she said the average CPC at $11.74 surged to $25.85 over the last six months, amounting to a 108% increase. However, there wasn’t an incremental return on sales.

“The level to which [price manipulations] happens is what we don’t know,” said Yang. “It’s shady business practices because there’s no regulation. They regulate themselves.”

Early in the history of search ads Google blocked trademark keyword bidding. They later allowed it. When keyword bidding on trademarks was allowed it led to a conundrum for some advertisers. If you do not defend your trademark you could lose it, but if you agree with competitors not to bid on each other's trademarks the FTC could come after you - like they did with 1-800 Contacts. This set up forces many brands to participate in auctions where they are arbitraging their own pre-existing brand equity. The ad auctioneer runs shady auctions where it looks across at your account behavior and bids then adjusts bid floors to suck more money out of you. This amounts to something akin to the bid jamming that was done in early Overture, except it is the house itself doing it to you! The last auction I remembered like that was SnapNames, where a criminal named Nelson Brady on the executive team used the handle halverez to leverage participant max bids and put in bids just under their bids. The goal of his fraud? To hit the numbers & get an earn out bonus - similar to how Google insiders were discussing "shaking the cushions" to hit the number.

Halverez created a program which looked across aggregate bid data, join auctions which only had 1 other participant, and then use the one-way view of competing bids to put in a shill bid to drive up costs - which sure sounds conceptually similar to Google's "shaking the cushions."

"Just looking at this very tactically, and sorry to go into this level of detail, but based on where we are I'm afraid it's warranted. We are short __% queries and are ahead on ads launches so are short __% revenue vs. plan. If we don't hit plan, our sales team doesn't get its quota for the second quarter in a row and we miss the street's expectations again, which is not what Ruth signaled to the street so we get punished pretty badly in the market. We are shaking the cushions on launches and have some candidates in May that will help, but if these break in mid-late May we only get half a quarter of impact or less, which means we need __% excess to where we are today and can't do it alone. The Search team is working together with us to accelerate a launch out of a new mobile layout by the end of May that will be very revenue positive (exact numbers still moving), but that still won't be enough. Our best shot at making the quarter is if we get an injection of at least __%, ideally __%, queries ASAP from Chrome. Some folks on our side are running a more detailed, Finance-based, what-if analysis on this and should be done with that in a couple of days, but I expect that these will be the rough numbers.

The question we are all faced with is how badly do we want to hit our numbers this quarter? We need to make this choice ASAP. I care more about revenue than the average person but think we can all agree that for all of our teams trying to live in high cost areas another $___,___ in stock price loss will not be great for morale, not to mention the huge impact on our sales team." - Google VP Jerry Dischler

Google is also pushing advertisers away from keyword-based bidding and toward a portfolio approach of automated bidding called Performance Max, where you give Google your credit card and budget then they bid as they wish. By blending everything into a single soup you may not know where the waste is & it may not be particularly easy to opt out of poorly performing areas. Remember enhanced AdWords campaigns?

Google continues to blur dataflow outside of their ad auctions to try to bring more of the ad spend into their auctions.

The amount Google is paying Apple to be the default search provider is staggering.

Tens of billions of dollars is a huge payday. No way Google would hyper-optimize other aspects of their business (locating data centers near dams, prohibiting use of credit card payments for large advertisers, cutting away ad agency management fees, buying Android, launching Chrome, using broken HTML on YouTube to make it render slowly on Firefox & Microsoft Edge to push Chrome distribution, all the dirty stuff Google did to violate user privacy with overriding Safari cookies, buying DoubleClick, stealing the ad spend from banned publishers rather than rebating it to advertisers, creating a proprietary version of HTML & force ranking it above other results to stop header bidding, & then routing around their internal firewall on display ads to give their house ads the advantage in their ad auctions, etc etc etc) and then just throw over a billion dollars a month needlessly at a syndication partner.

For perspective on the scale of those payments consider that it wasn't that long ago Yahoo! was considered a big player in search and Apollo bought Yahoo! plus AOL from Verizon for about $5 billion & then was quickly able to sell branding & technology rights in Japan to Softbank for $1.6 billion & other miscellaneous assets for nearly a half-billion, reducing the net cost to only $3 billion.

If Google loses this lawsuit and the payments to Apple are declared illegal, that would be a huge revenue (and profit) hit for Apple. Apple would be forced to roll out their own search engine. This would cut away at least 30% of the search market from Google & it would give publishers another distribution channel. Most likely Apple Search would launch with a lower ad density than Google has for short term PR purposes & publishers would have a year or two of enhanced distribution before Apple's ad load matched Google's ad load.

It is hard to overstate how strong Apple's brand is. For many people the cell phone is like a family member. I recently went to upgrade my phone and Apple's local store closed early in the evening at 8pm. The next day when they opened at 10 there was a line to wait in to enter the store, like someone was trying to get concert tickets. Each privacy snafu from Google helps strengthen Apple's relative brand position.

Google has also diluted the quality of their own brand by rewriting search queries excessively to redirect traffic flows toward more commercial interests. Wired covered how Project Mercury works:

This onscreen Google slide had to do with a “semantic matching” overhaul to its SERP algorithm. When you enter a query, you might expect a search engine to incorporate synonyms into the algorithm as well as text phrase pairings in natural language processing. But this overhaul went further, actually altering queries to generate more commercial results. ... Most scams follow an elementary bait-and-switch technique, where the scoundrel lures you in with attractive bait and then, at the right time, switches to a different option. But Google “innovated” by reversing the scam, first switching your query, then letting you believe you were getting the best search engine results. This is a magic trick that Google could only pull off after monopolizing the search engine market, giving consumers the false impression that it is incomparably great, only because you’ve grown so accustomed to it.

The mobile search results on Google require at least a screen or two of scrolls to get to the organic results if there is a hint of commercial intent behind the search query. Once they have monetized the real estate they are reliant on broader economic growth & using ad buy bundling to drive cross-subsidies of other non-search ad inventory, which may contain more than a bit of fraud. Performance Max may max out your spend without actually performing for anybody other than Google.

Google not only shill bid on lower competition terms to squeeze defensive brand bids and boost auction floor pricing, but they also implemented shill bids in competitive ad auctions:

Michael Whinston, a professor of economics at the Massachusetts Institute of Technology, said Friday that Google modified the way it sold text ads via “Project Momiji” – named for the wooden Japanese dolls that have a hidden space for friends to exchange secret messages. The shift sought “to raise the prices against the highest bidder,” Whinston told Judge Amit Mehta in federal court in Washington.

While Google's search marketshare is rock solid, the number of search engines available has increased significantly over the past few years. Not only is there Bing and DuckDuckGo but the tail is longer than it was a few years back. In addition to regional players like Baidu and Yandex there's now Brave Search, Mojeek, Qwant, Yep, and You. GigaBlast and Neeva went away, but anything that prohibits selling defaults to a company with over 90% marketshare will likely lead to dozens more players joining the search game. Search traffic will remain lucrative for whoever can capture it, as no matter how much Google tries to obfuscate marketing data the search query reflects the intent of the end user.

“Search advertising is one of the world’s greatest business models ever created…there are certainly illicit businesses (cigarettes or drugs) that could rival these economics, but we are fortunate to have an amazing business.” - Google VP of Finance Mike Roszak

AI-Driven Search

I just dusted off the login here to realize I hadn't posted in about a half-year & figured it was time to write another one. ;)

Yandex Source Code Leak

Some of Yandex's old source code was leaked, and few cared about the ranking factors shared in the leak.

Mike King made a series of Tweets on the leak.

The signals used for ranking included things like link age

and user click data including visit frequency and dwell time

Google came from behind and was eating Yandex's lunch in search in Russia, particularly by leveraging search default bundling in Android. The Russian antitrust regulator nixed that and when that was nixed, Yandex regained strength. Of course the war in Ukraine has made everything crazy in terms of geopolitics. That's one reason almost nobody cared about the Yandex data link. And the other reason is few could probably make sense of understanding what all the signals are or how to influence them.

The complexity of search - when it is a big black box which has big swings 3 or 4 times a year - shifts any successful long term online publishers away from being overly focused on information retrieval and ranking algorithms to focus on the other aspects of publishing which will hopefully paper over SEO issues. Signs of a successful & sustainable website include:

  • It remains operational even if a major traffic source goes away.
  • People actively seek it out.
  • If a major traffic source cuts its distribution people notice & expend more effort to seek it out.

As black box as search is today, it is only going to get worse in the coming years.

ChatGPT Hype

The hype surrounding ChatGPT is hard to miss. Fastest growing user base. Bing integration. A sitting judge using the software to help write documents for the court. And, of course, the get-rich-quick crew is out in full force.

Some enterprising people with specific professional licenses may be able to mint money for a window of time

but for most people the way to make money with AI will be doing something that AI can not replicate.

Bing Integration of Open AI Technology

The New Bing integrated OpenAI's ChatGPT technology to allow chat-based search sessions which ingest web content and use it to create something new, giving users direct answers and allowing re-probing for refinements. Microsoft stated the AI features also improved their core rankings outside of the chat model: "Applying AI to core search algorithm. We’ve also applied the AI model to our core Bing search ranking engine, which led to the largest jump in relevance in two decades. With this AI model, even basic search queries are more accurate and more relevant."

Fawning Coverage

Some of the tech analysis around the AI algorithms is more than a bit absurd. Consider this passage:

the information users input into the system serves as a way to improve the product. Each query serves as a form of feedback. For instance, each ChatGPT answer includes thumbs up and thumbs down buttons. A popup window prompts users to write down the “ideal answer,” helping the software learn from its mistakes.

A long time ago the Google Toolbar had a smiley face and a frown face on it. The signal there was basically pure spam. At one point Matt Cutts mentioned Google would look at things that got a lot of upvotes to see how else they were spamming. Direct Hit was also spammed into oblivion many years before that.

In some ways the current AI search stuff is trying to re-create Ask Jeeves, but Ask had already lost to Google long ago. The other thing AI search is similar to is voice assistant search. Maybe the voice assistant search stuff which has largely failed will get a new wave of innovation, but the current AI search stuff is simply a text interface of the voice search stuff with a rewrite of the content.

High Confidence, But Often Wrong

There are two other big issues with correcting an oracle.

  • You'll lose your trust in an oracle when you repeatedly have to correct it.
  • If you know the oracle is awful in your narrow niche of expertise you probably won't trust it on important issues elsewhere.

Beyond those issues there is the concept of blame or fault. When a search engine returns a menu of options if you pick something that doesn't work you'll probably blame yourself. Whereas if there is only a single answer you'll lay blame on the oracle. In the answer set you'll get a mix of great answers, spam, advocacy, confirmation bias, politically correct censorship, & a backward looking consensus...but you'll get only a single answer at a time & have to know enough background & have enough topical expertise to try to categorize it & understand the parts that were left out.

We are making it easier and cheaper to use software to re-represent existing works, at the same time we are attaching onerous legal liabilities to building something new.

Creating A Fuzy JPEG

This New Yorker article did a good job explaining the concept of lossy compression:

"The fact that Xerox photocopiers use a lossy compression format instead of a lossless one isn’t, in itself, a problem. The problem is that the photocopiers were degrading the image in a subtle way, in which the compression artifacts weren’t immediately recognizable. If the photocopier simply produced blurry printouts, everyone would know that they weren’t accurate reproductions of the originals. What led to problems was the fact that the photocopier was producing numbers that were readable but incorrect; it made the copies seem accurate when they weren’t. ... If you ask GPT-3 (the large-language model that ChatGPT was built from) to add or subtract a pair of numbers, it almost always responds with the correct answer when the numbers have only two digits. But its accuracy worsens significantly with larger numbers, falling to ten per cent when the numbers have five digits. Most of the correct answers that GPT-3 gives are not found on the Web—there aren’t many Web pages that contain the text “245 + 821,” for example—so it’s not engaged in simple memorization. But, despite ingesting a vast amount of information, it hasn’t been able to derive the principles of arithmetic, either. A close examination of GPT-3’s incorrect answers suggests that it doesn’t carry the “1” when performing arithmetic."

Exciting New Content Farms

Ted Chiang then goes on to explain the punchline ... we are hyping up eHow 2.0:

Even if it is possible to restrict large language models from engaging in fabrication, should we use them to generate Web content? This would make sense only if our goal is to repackage information that’s already available on the Web. Some companies exist to do just that—we usually call them content mills. Perhaps the blurriness of large language models will be useful to them, as a way of avoiding copyright infringement. Generally speaking, though, I’d say that anything that’s good for content mills is not good for people searching for information. The rise of this type of repackaging is what makes it harder for us to find what we’re looking for online right now; the more that text generated by large language models gets published on the Web, the more the Web becomes a blurrier version of itself.

The same New Yorker article mentioned the concept that if the AI was great it should trust its own output as input for making new versions of its own algorithms, but how could it score itself against itself when its own flaws are embedded recursively in layers throughout algorithmic iteration without any source labeling?

Testing on your training data is considered a cardinal rule machine learning error. Using prior output as an input creates similar problems.

Each time AI eats a layer of the value chain it leaves holes in the ecosystem, where the primary solution is to pay for what was once free. Even the "buy nothing" movements have a commercial goal worth fighting over.

As AI offers celebrity voices, impersonate friends, track people, automates marketing, and creates deep fake celebrity-like content, it will move more of social media away from ad revenue over to a subscription-based model. Twitter's default "for you" tab will only recommend content from paying subscribers. People will subscribe to and pay for a confirmation bias they know (even - or especially - if it is not approved within the state-preferred set of biases), provided there is a person & a personality associated with it. They'll also want any conversations with AI agents remain private.

When the AI stuff was a ragtag startup with little to lose the label "open" was important to draw interest. As commercial prospects improved with the launch of GPT-4 they shifted away from the "open," explaining the need for secrecy for both safety and competitive reasons. Much of the wow factor in generative AI is in recycling something while dropping the source to make something appear new while being anything but. And then the first big money number is the justification for further investments in add ons & competitors.

Google's AI Strategy

Google fast followed Bing's news with a vapoware announcement of Bard. Some are analyzing Google letting someone else go first as being a sign Google is behind the times and is getting caught out by an upstart.

Google bought DeepMind in 2014 for around $600 million. They've long believed in AI technology, and clearly lead the category, but they haven't been using it to re-represent third party content in the SERPs to the degree Microsoft is now doing in Bing.

My view is Google had to let someone else go first in order to defuse any associated antitrust heat. "Hey, we are just competing, and are trying to stay relevant to change with changing consumer expectations" is an easier sell when someone else goes first. One could argue the piss poor reception to the Bard announcement is actually good for Google in the longterm as it makes them look like they have stronger competition than they do, rather than being a series of overlapping monopoly market positions (in search, web browser, web analytics, mobile operating system, display ads, etc.)

Google may well have major cultural problems, but "They are all the natural consequences of having a money-printing machine called “Ads” that has kept growing relentlessly every year, hiding all other sins. (1) no mission, (2) no urgency, (3) delusions of exceptionalism, (4) mismanagement," though Google is not far behind in AI. Look at how fast they opened up Bard to end users.

AI = Money / Increased Market Cap

The capital markets are the scorecard for capitalism. It is hard to miss how much the market loved the Bing news for Microsoft & how bad the news was for Google.

Millions Suddenly Excited About Bing

In a couple days over a million people signed up to join a Bing wait list.

Your Margin is My Opportunity

Microsoft is pitching this as a margin compression play for Google

that may also impact their TAC spend

ChatGPT costs around a couple cents per conversation: "Sam, you mentioned in a tweet that ChatGPT is extremely expensive on the order of pennies per query, which is an astronomical cost in tech. SA: Per conversation, not per query."

The other side of potential margin compression comes from requiring additional computing power to deliver results:

Our sources indicate that Google runs ~320,000 search queries per second. Compare this to Google’s Search business segment, which saw revenue of $162.45 billion in 2022, and you get to an average revenue per query of 1.61 cents. From here, Google has to pay for a tremendous amount of overhead from compute and networking for searches, advertising, web crawling, model development, employees, etc. A noteworthy line item in Google’s cost structure is that they paid in the neighborhood of ~$20B to be the default search engine on Apple’s products.

Beyond offering a conversational interface, Bing is also integrating AI content directly in their search results on some search queries. It goes *BELOW* all the ads & *ABOVE* the organic results.

The above sort of visual separator eye candy has historically had a net effect of shifting click distributions away from organics toward the ads. It is why Google features "people also ask" and similar in their search results.

AI is the New Crypto

Microsoft is pitching that even when AI is wrong it can offer "usefully" wrong answers. And a lot of the "useful" wrong stuff can also be harmful: "there are a ton of very real ways in which this technology can be used for harm. Just a few: Generating spam, Automated romance scams, Trolling and hate speech ,Fake news and disinformation, Automated radicalization (I worry about this one a lot)"

"I knew I had just seen the most important advance in technology since the graphical user interface. This inspired me to think about all the things that AI can achieve in the next five to 10 years. The development of AI is as fundamental as the creation of the microprocessor, the personal computer, the Internet, and the mobile phone. It will change the way people work, learn, travel, get health care, and communicate with each other. Entire industries will reorient around it. Businesses will distinguish themselves by how well they use it." - Bill Gates

Since AI is the new crypto, everyone is integrating it, if only in press release format, while banks ban it. All of Microsoft's consumer-facing & business-facing products are getting integrations. Google is treating AI as the new Google+.

Remember all the hype around STEM? If only we can churn out more programmers? Learn to code!

Well, how does that work out if the following is true?

"The world now realizes that maybe human language is a perfectly good computer programming language, and that we've democratized computer programming for everyone, almost anyone who could explain in human language a particular task to be performed." - Nvidia CEO Jensen Huang

AI is now all over Windows. And for a cherry on top of the hype cycle:

A gradual transition gives people, policymakers, and institutions time to understand what’s happening, personally experience the benefits and downsides of these systems, adapt our economy, and to put regulation in place. It also allows for society and AI to co-evolve, and for people collectively to figure out what they want while the stakes are relatively low.

We believe that democratized access will also lead to more and better research, decentralized power, more benefits, and a broader set of people contributing new ideas. As our systems get closer to AGI, we are becoming increasingly cautious with the creation and deployment of our models.

We have a nonprofit that governs us and lets us operate for the good of humanity (and can override any for-profit interests), including letting us do things like cancel our equity obligations to shareholders if needed for safety and sponsor the world’s most comprehensive UBI experiment.

Algorithmic Publishing

The algorithms that allow dirt cheap quick rewrites won't be used just by search engines re-representing publisher content, but also by publishers to churn out bulk content on the cheap.

After Red Ventures acquired cNet they started publishing AI content. The series of tech articles covering that AI content lasted about a month and only ended recently. In the past it was the sort of coverage which would have led to a manual penalty, but with the current antitrust heat Google can't really afford to shake the boat & prove their market power that way. In fact, Google's editorial stance is now such that Red Ventures can do journalist layoffs in close proximity to that AI PR blunder.

Men's Journal also had AI content problems.

AI content poured into a trusted brand monetizes the existing brand equity until people (and algorithms) learn not to trust the brands that have been monetized that way.

A funny sidebar here is the original farmer update that aimed at eHow skipped hitting eHow because so many journalists were writing about how horrible eHow was. These collective efforts to find the best of the worst of eHow & constantly writing about it made eHow look like a legitimately sought after branded destination. Google only downranked eHow after collecting end user data on a toolbar where angry journalists facing less secure job prospects could vote to nuke eHow, thus creating the "signal" that eHow rankings deserve to be torched. Demand Media's Livestrong ranked well far longer than eHow did.


The process of pouring low cost backfill into a trusted masthead is the general evolution of online media ecosystems:

This strategy meant that it became progressively harder for shoppers to find things anywhere except Amazon, which meant that they only searched on Amazon, which meant that sellers had to sell on Amazon. That's when Amazon started to harvest the surplus from its business customers and send it to Amazon's shareholders. Today, Marketplace sellers are handing 45%+ of the sale price to Amazon in junk fees. The company's $31b "advertising" program is really a payola scheme that pits sellers against each other, forcing them to bid on the chance to be at the top of your search. ... once those publications were dependent on Facebook for their traffic, it dialed down their traffic. First, it choked off traffic to publications that used Facebook to run excerpts with links to their own sites, as a way of driving publications into supplying fulltext feeds inside Facebook's walled garden. This made publications truly dependent on Facebook – their readers no longer visited the publications' websites, they just tuned into them on Facebook. The publications were hostage to those readers, who were hostage to each other. Facebook stopped showing readers the articles publications ran, tuning The Algorithm to suppress posts from publications unless they paid to "boost" their articles to the readers who had explicitly subscribed to them and asked Facebook to put them in their feeds. ... "Monetize" is a terrible word that tacitly admits that there is no such thing as an "Attention Economy." You can't use attention as a medium of exchange. You can't use it as a store of value. You can't use it as a unit of account. Attention is like cryptocurrency: a worthless token that is only valuable to the extent that you can trick or coerce someone into parting with "fiat" currency in exchange for it. You have to "monetize" it – that is, you have to exchange the fake money for real money. ... Even with that foundational understanding of enshittification, Google has been unable to resist its siren song. Today's Google results are an increasingly useless morass of self-preferencing links to its own products, ads for products that aren't good enough to float to the top of the list on its own, and parasitic SEO junk piggybacking on the former.

Bing finally won a PR battle against Google & Microsoft is shooting themselves in the foot by undermining the magic & imagination of the narrative by pushing more strict chat limits, increasing search API fees, testing ads in the AI search results, and threating to cut off search syndication partners if the index is used to feed AI chatbots.

The enshitification concept feels more like a universal law than a theory.

When Yahoo, Twitter & Facebook underperform and the biggest winners like Google, Microsoft, and Amazon are doing big layoff rounds, everyone is getting squeezed.

AI rewrites accelerates the squeeze:

"When WIRED asked the Bing chatbot about the best dog beds according to The New York Times product review site Wirecutter, which is behind a metered paywall, it quickly reeled off the publication’s top three picks, with brief descriptions for each." ... "OpenAI is not known to have paid to license all that content, though it has licensed images from the stock image library Shutterstock to provide training data for its work on generating images."

The above is what Paul Kedrosky was talking about when he wrote of AI rewrites in search being a Tragedy of the Commons problem.

A parallel problem is the increased cost of getting your science fiction short story read when magazines shut down submissions due to a rash of AI-spam submissions:

The rise of AI-powered chatbots is wreaking havoc on the literary world. Sci-fi publication Clarkesworld Magazine is temporarily suspending short story submissions, citing a surge in people using AI chatbots to “plagiarize” their writing.

The magazine announced(Opens in a new window) the suspension days after Clarkesworld editor Neil Clarke warned about AI-written works posing a threat to the entire short-story ecosystem.

Warnings Serving As Strategy Maps

"He who fights with monsters might take care lest he thereby become a monster. And if you gaze for long into an abyss, the abyss gazes also into you." - Nietzsche

Going full circle here, early Google warned against ad-driven search engines, then Google became the largest ad play in the world. Similarly ...

Elon wants to create a non-woke AI, but he'll still have some free speech issues.

Over time more of the web will be "good enough" rewrites, and the JPEG will keep getting fuzzier:

"This new generation of chat-based search engines are better described as “answer engines” that can, in a sense, “show their work” by giving links to the webpages they deliver and summarize. But for an answer engine to have real utility, we’re going to have to trust it enough, most of the time, that we accept those answers at face value. ... The greater concentration of power is all the more important because this technology is both incredibly powerful and inherently flawed: it has a tendency to confidently deliver incorrect information. This means that step one in making this technology mainstream is building it, and step two is minimizing the variety and number of mistakes it inevitably makes. Trust in AI, in other words, will become the new moat that big technology companies will fight to defend. Lose the user’s trust often enough, and they might abandon your product. For example: In November, Meta made available to the public an AI chat-based search engine for scientific knowledge called Galactica. Perhaps it was in part the engine’s target audience—scientists—but the incorrect answers it sometimes offered inspired such withering criticism that Meta shut down public access to it after just three days, said Meta chief AI scientist Yann LeCun in a recent talk."

Check out the sentence Google chose to bold here:

As the economy becomes increasingly digital the AI algorithms have deep implications across the economy. Things like voice rights, knock offs, virtual re-representations, source attribution, copyright of input, copyright of output, and similar are obvious. But how far do we allow algorithms to track a person's character flaws and exploit them? Horse racing ads that follow a gambling addict around the web, or a girl with anorexia who keeps clicking on weight loss ads.

One of the biggest use cases for paid AI chatbots so far is fantasty sexting. It is far easier to program a lovebot filled with confirmation bias than it is to improve oneself. Digital soma.

When AI is connected directly to the Internet and automates away many white collar jobs what comes next? As AI does everything for you do the profit margins shift across from core product sales to hidden junk fees (e.g. ticket scalper marketplaces or ordering flowers for Mother's Day where you get charged separately for shipping, handling, care, weekend shipping, Sunday shipping, holiday shipping)?

"LLMs aren’t just the biggest change since social, mobile, or cloud–they’re the biggest thing since the World Wide Web. And on the coding front, they’re the biggest thing since IDEs and Stack Overflow, and may well eclipse them both. But most of the engineers I personally know are sort of squinting at it and thinking, “Is this another crypto?” Even the devs at Sourcegraph are skeptical. I mean, what engineer isn’t. Being skeptical is a survival skill. ... The punchline, and it’s honestly one of the hardest things to explain, so I’m going the faith-based route today, is that all the winners in the AI space will have data moats." - Steve Yegge

Monopoly Bundling

The thing that makes the AI algorithms particularly dangerous is not just that they are often wrong while appearing high-confidence, it is that they are tied to monopoly platforms which impact so many other layers of the economy. If Google pays Apple billions to be the default search provider on iPhone any error in the AI on a particular topic will hit a whole lot of people on Android & Apple devices until the problem becomes a media issue & gets fixed.

The analogy here would be if Coca Cola had a poison and they also poured Pepsi products.

These cloud platforms also want to help retailers manage in-store inventory:

Google Cloud said Friday its algorithm can recognize and analyze the availability of consumer packaged goods products on shelves from videos and images provided by the retailer’s own ceiling-mounted cameras, camera-equipped self-driving robots or store associates. The tool, which is now in preview, will become broadly available in the coming months, it said. ... Walmart Inc. notably ended its effort to use roving robots in store aisles to keep track of its inventory in 2020 because it found different, sometimes simpler solutions that proved just as useful, said people familiar with the situation.

Microsoft has a browser extension for adding coupons to website checkouts. Google is also adding coupon features to their SERPs.

Every ad network can use any OS, email, or web browser hooks to try to reset user defaults & suck users into that particular ecosystem.

AI Boundaries

Generative AI algorithms will always have a bias toward being backward looking as it can only recreate content based off of other ingested content that has went through some editorial process. AI will also overemphasize the recent past, as more dated cultural references can represent an unneeded risk & most forms of spam will target things that are sought after today. Algorithmic publishing will lead to more content created each day.

From a risk perspective it makes sense for AI algorithms to promote consensus views while omitting or understating the fringe. Promoting fringe views represents risk. Promoting consensus does not.

Each AI algorithm has limits & boundaries, with humans controlling where they are set. Injection attacks can help explore some of the boundaries, but they'll patch until probed again.

Boundaries will often be set by changing political winds:

"The tech giant plans to release a series of short videos highlighting the techniques common to many misleading claims. The videos will appear as advertisements on platforms like Facebook, YouTube or TikTok in Germany. A similar campaign in India is also in the works. It’s an approach called prebunking, which involves teaching people how to spot false claims before they encounter them. The strategy is gaining support among researchers and tech companies. ... When catalyzed by algorithms, misleading claims can discourage people from getting vaccines, spread authoritarian propaganda, foment distrust in democratic institutions and spur violence."

Stating facts about population subgroups will be limited in some ways to minimize perceived racism, sexism, or other fringe fake victim group benefits fund flows. Never trust Marxists who own multiple mansions.

At the same time individual journalists can drop napalm on any person who shares too many politically incorrect facts.

Some things are quickly labeled or debunked. Other things are blown out of proportion to scare and manipulate people:

Dr. Ioannidis et. al. found that across 31 national seroprevalence studies in the pre-vaccine era, the median IFR was 0.0003% at 0-19 years, 0.003% at 20-29 years, 0.011% at 30-39 years, 0.035% at 40-49 years, 0.129% at 50-59 years, and 0.501% at 60-69 years. This comes out to 0.035% for those aged 0-59 and 0.095% for those aged 0-69.

The covid response cycle sacrificed childhood development (and small businesses) to offer fake protections to unhealthy elderly people (and bountiful subsidies to large "essential" corporations).

‘Civilisation and barbarism are not different kinds of society. They are found – intertwined – whenever human beings come together.’ This is true whether the civilisation be Aztec or Covidian. A future historian may compare the superstition of the Aztec to those of the Covidian. The ridiculous masks, the ineffective lockdowns, the cult-like obedience to authority. It’s almost too perfect that Aztec nobility identified themselves by walking with a flower held under the nose.

A lot of children had their childhoods destroyed by the idiotic lockdowns. And a lot of those children are now destroying the lives of other children:

In the U.S., homicides committed by juveniles acting alone rose 30% in 2020 from a year earlier, while those committed by multiple juveniles increased 66%. The number of killings committed by children under 14 was the highest in two decades, according to the most recent federal data.

Now we get to pile inflation and job insecurity on top of those headwinds to see more violence.

The developmental damage (school closed, stressed out parents, hidden faces, less robust immune systems, limited social development) is hard to overstate:

The problem with this is that the harm of performative art in this regard is not speculative, particularly in young children where language development is occurring and we know a huge percentage of said learning comes from facial expressions which of course a mask prevents from being seen. Every single person involved in this must face criminal sanction and prison for the deliberate harm inflicted upon young children without any evidence of benefit to anyone. When the harm is obvious and clear but the benefit dubious proceeding with a given action is both stupid and criminal.

Some entities will claim their own statements are conspiracy theory, even when directly quoted:

“If Russia invades . . . there will be no longer a Nord Stream 2. We will bring an end to it.” - President Joseph R. Biden

In an age of deep fakes, confirmation bias driven fast social shares (filter bubble), legal threats, increased authenticity of impersonation technology, AI algorithms which sort & rewrite media, & secret censorship programs ... who do you trust? How are people informed when nation states offer free global internet access with a thumb on the scale of truth, even as aggregators block access to certain sources demanding payments?

Lab leaks sure sound a lot like an outbreak of chocolatey goodness in Hershey, PA!

"The fact that protesters could be at once both the victims and perpetrators of misinformation simply shows how pernicious misinformation is in modern society." - Canadian Justice Paul Rouleau

What is freedom?

By 2016, however, the WEF types who’d grown used to skiing at Davos unmolested and cheering on from Manhattan penthouses those thrilling electoral face-offs between one Yale Bonesman and another suddenly had to deal with — political unrest? Occupy Wall Street was one thing. That could have been over with one blast of the hose. But Trump? Brexit? Catalan independence? These were the types of problems you read about in places like Albania or Myanmar. It couldn’t be countenanced in London or New York, not for a moment. Nobody wanted elections with real stakes, yet suddenly the vote was not only consquential again, but “often existentially so,” as American Enterprise Institute fellow Dalibor Rohac sighed. So a new P.R. campaign was born, selling a generation of upper-class kids on the idea of freedom as a stalking-horse for race hatred, ignorance, piles, and every other bad thing a person of means can imagine

New Google Ad Labeling

TechCrunch recently highlighted how Google is changing their ad labeling on mobile devices.

A few big changes include:

  • ad label removed from individual ad units
  • where the unit-level label was instead becomes a favicon
  • a "Sponsored" label above ads
  • the URL will show right of the favicon & now the site title will be in a slightly larger font above the URL

An example of the new layout is here:
2022 Google SERP layouts with new ad labeling

Displaying a site title & the favicon will allow advertisers to get brand exposure, even if they don't get the click, while the extra emphasis on site name could lead to shifting of ad clicks away from unbranded sites toward branded sites. It may also cause a lift in clicks on precisely matching domains, though that remains to be seen & likely dependes upon many other factors. The favicon and site name in the ads likely impact consumer recall, which can bleed into organic rankings.

After TechCrunch made the above post a Google spokesperson chimed in with an update

Changes to the appearance of Search ads and ads labeling are the result of rigorous user testing across many different dimensions and methodologies, including user understanding and response, advertiser quality and effectiveness, and overall impact of the Search experience. We’ve been conducting these tests for more than a year to ensure that users can identify the source of their Search ads and where they are coming from, and that paid content is clearly labeled and distinguishable from search results as Google Search continues to evolve

The fact it was pre-announced & tested for so long indicates it is both likely to last a while and will in aggregate shift clicks away from the organic result set to the paid ads.

Google Helpful Content Update

Granular Panda

Reading the tea leaves on the pre-announced Google "helpful content" update rolling out next week & over the next couple weeks in the English language, it sounds like a second and perhaps more granular version of Panda which can take in additional signals, including how unique the page level content is & the language structure on the pages.

Like Panda, the algorithm will update periodically across time & impact websites on a sitewide basis.

Cold Hot Takes

The update hasn't even rolled out yet, but I have seen some write ups which conclude with telling people to use an on-page SEO tool, tweets where people complained about low end affiliate marketing, and gems like a guide suggesting empathy is important yet it has multiple links on how to do x or y "at scale."

Trashing affiliates is a great sales angle for enterprise SEO consultants since the successful indy affiliate often knows more about SEO than they do, the successful affiliate would never become their client, and the corporation that is getting their asses handed to them by an affiliate would like to think this person has the key to re-balance the market in their own favor.

My favorite pre-analysis was a person who specialized in ghostwriting books for CEOs Tweeting that SEO has made the web too inauthentic and too corporate. That guy earned a star & a warm spot in my heart.

Profitable Publishing

Of course everything in publishing is trade offs. That is why CEOs hire ghostwriters to write books for them, hire book launch specialists to manipulate the best seller lists, or even write messaging books in the first place. To some Dan Price was a hero advocating for greater equality and human dignity. To others he was a sort of male feminist superhero, with all the Harvey Weinstein that typically entails.

Anyone who has done 100 interviews with journalists see ones that do their job by the book and aim to inform their readers to the best of their abilities (my experiences with the Wall Street Journal & PBS were aligned with this sort of ideal) and then total hatchet jobs where a journalist plants a quote they want & that they said, that they then attributes it to you (e.g. London Times freelance journalist).

There are many dimensions to publishing:

  • depth
  • purpose
  • timing
  • audience
  • language
  • experience
  • format
  • passion
  • uniqueness
  • frequency

Blogs to Feeds

For a long time indy blogs punched well above their weight due to the incestuous nature of cross-referencing each other, the speed of publishing when breaking news, and how easy feed readers made it to subscribe to your favorite blogs. Google Reader then ate the feed reader market & shut down. And many bloggers who had unique things to say eventually started to repeat themselves. Or their passions & interests changed. Or their market niche disappeared as markets moved on. Starting over is hard & staying current after the passion fades is difficult. Plus if you were rather successful it is easy to become self absorbed and/or lose the hunger and drive that initially made you successful.

Around the same time blogs started sliding people spent more and more time on various social networks which hyper-optimized the slot machine type dopamine rush people get from refreshing the feed. Social media largely replaced blogs, while legacy media publishers got faster at putting out incomplete news stories to be updated as they gather more news. TikTok is an obvious destination point for that dopamine rush - billions of short pieces of content which can be consumed quickly and shared - where the user engagement metrics for each user are tracked and aggregated across each snippet of media to drive further distribution.

Burnout & Changing Priorities

I know one of the reasons I blog less than I used to is a lot of the things I would write would be repeats. Another big reason was when my wife was pregnant I decided to shut down our membership site so I could take my wife for a decently long walk almost everyday so her health was great when it came time to give birth & ensure I had spare capacity for if anything went wrong with the pregnancy process. As a kid my dad was only around much for a few summers and I wanted to be better than that for my kid.

The other reason I cut back on blogging is at some point search went from a endless blue water market to a zero sum game to a negative sum game (as ad clicks displaced organic clicks). And in such an environment if you have a sustainable competitive advantage it is best to lean into it yourself as hard as you can rather than sharing it with others. Like when we had an office here our link builders I trained were getting awesome unpaid links from high-trust sources for what backed out to about $25 of labor time (and no more than double that after factoring in office equipment, rent, etc.).

If I share that script / process on the blog publicly I would move the economics against myself. At the end of the day business is margins, strategy, market, and efficiency. Any market worth being in is going to have competition, so you need to have some efficiency or strategic differentiators if you are going to have sustainable profit margins. I've paid others many multiples of that for link building for many years back when links were the primary thing driving rankings.

I don't know the business model where sharing the above script earns more than it costs. Does one launch a Substack priced at like $500 or $1,000 a month where they offer a detailed guide a month? How many people adopt the script before the response rates fall & it offsets the costs by more than the revenues? My issue with consulting is I always wanted to over-deliver for clients & always ended up selling myself short when compared to publishing, so I just stick with a few great clients and a bit of this and that vs going too deep & scaling up there. Plus I had friends who went big and then some of their clients who were acquired had the acquirer brag about the SEO, that lead to a penalty, then the acquirer of the client threw the SEO under the bus and had their business torched.

When you have a kid seeing them learn and seeing wonderment in their eyes is as good as life gets, but if you undermine your profit margins you'd also be directly undermining your own child's future ... often to help people who may not even like you anyhow. That is ultimately self defeating as it gets, particularly as politics grow more polarized & many begin to view retribution as a core function of government.

I believe there are no limits to the retributive and malicious use of taxation as a political weapon. I believe there are no limits to the retributive and malicious use of spending as a political reward.


The role of search engines is to suck as much of the margins as they can out of publishing while trying to put some baseline floor on content quality so that people would still prefer to use a search engine rather than some other reference resource. Google sees memes like "add Reddit to the end of your search for real content" as an attack on their own brand. Google needs periodic large shake ups to reaffirm their importance, maintain narrative control around innovation, and to shake out players with excessive profit margins who were too well aligned with the current local maxima. Google needs aggressive SEO efforts with large profits to have an "or else" career risk to them to help reign in such efforts.

You can see the intent for career risk in how the algorithm will wait months to clear the flag:

Google said the helpful content update system is automated, regularly evaluating content. So the algorithm is constantly looking at your content and assigning scores to it. But that does not mean, that if you fix your content today, your site will recover tomorrow. Google told me there is this validation period, a waiting period, for Google to trust that you really are committed to updating your content and not just updating it today, Google then ranks you better and then you put your content back to the way it was. Google needs you to prove, over several months - yes - several months - that your content is actually helpful in the long run.

If you thought a site were quality, had some issues, the issues were cleaned up, and you were still going to wait to rank it appropriately ... the sole and explicit purpose of that delay is career risk to others to prevent them flying to close to the sun - to drive self regulation out of fear.

Brand counts for a lot in search & so does buying the default placement position - look at how much Google pays Apple to not compete in search, or look at how Google had that illegal ad auction bid rigging gentleman's agreement with Facebook to not compete with a header bidding solution so Google could maintain their outsized profit margins on ad serving on third party websites.

Business ultimately is competition. Does Google serve your ads? What are the prices charged to players on each side of each auction & how much rake can the auctioneer capture for themselves?

The Auctioneer's Shill Bid - Google Halverez (beta)

That is why we see Google embedding more features directly in their search results where they force rank their vertical listings above the organic listings. Their vertical ads are almost always placed above organics & below the text AdWords ads. Such vertical results could be thought of as a category-based shill bid to try to drive attention back upward, or move traffic into a parallel page where there is another chance to show more ads.

This post stated:

Google runs its search engine partly on its internally developed Cloud TPU chips. The chips, which the company also makes available to other organizations through its cloud platform, are specifically optimized for artificial intelligence workloads. Google’s newest Cloud TPU can provide up to 275 teraflops of performance, which is equivalent to 275 trillion computing operations per second.

Now that computing power can be run across:

  • millions of books Google has indexed
  • particular publishers Google considers "above board" like Reuters, AP, the New York Times, the Wall Street Journal, etc.
  • historically archived content from trusted publishers before "optimizing for search" was actually a thing

... and model language usage versus modeling the language usage of publishers known to have weak engagement / satisfaction metrics.

Low end outsourced content & almost good enough AI content will likely tank. Similarly textually unique content which says nothing original or is just slapped together will likely get downranked as well.

Expect Volatility

They would not have pre-announced the update & gave some people some embargoed exclusives unless there was going to be a lot of volatility. As typical with the bigger updates, they will almost certainly roll out multiple other updates sandwiched together to help obfuscate what signals they are using & misdirect people reading too much in the winners and losers lists.

Here are some questions Google asked:

  • Do you have an existing or intended audience for your business or site that would find the content useful if they came directly to you?
  • Does your content clearly demonstrate first-hand expertise and a depth of knowledge (for example, expertise that comes from having actually used a product or service, or visiting a place)?
  • Does your site have a primary purpose or focus?
  • After reading your content, will someone leave feeling they’ve learned enough about a topic to help achieve their goal?
  • Will someone reading your content leave feeling like they’ve had a satisfying experience?
  • Are you keeping in mind our guidance for core updates and for product reviews?

As a person who has ... erm ... put a thumb on the scale for a couple decades now, one can feel the algorithmic signals approximated by the above questions.

To the above questions they added:

  • Is the content primarily to attract people from search engines, rather than made for humans?
  • Are you producing lots of content on different topics in hopes that some of it might perform well in search results?
  • Are you using extensive automation to produce content on many topics?
  • Are you mainly summarizing what others have to say without adding much value?
  • Are you writing about things simply because they seem trending and not because you'd write about them otherwise for your existing audience?
  • Does your content leave readers feeling like they need to search again to get better information from other sources?
  • Are you writing to a particular word count because you've heard or read that Google has a preferred word count? (No, we don't).
  • Did you decide to enter some niche topic area without any real expertise, but instead mainly because you thought you'd get search traffic?
  • Does your content promise to answer a question that actually has no answer, such as suggesting there's a release date for a product, movie, or TV show when one isn't confirmed?

Some of those indicate where Google believes the boundaries of their own role as a publisher are & that you should stay out of their lane. :D

Barrier to Entry vs Personality

One of the interesting things about the broader scope of algorithm shifts is each thing that makes the algorithms more complex, increases barrier to entry, and increases cost ultimately increases the chunk size of competition. And when that is done what is happening is the macroparasite is being preference over the microparasite. Conceptually Google has a lot of reasons to have that bias or preference:

  • fewer entities to police (lower cost)
  • more data to use to police each entity (higher confidence)
  • easier to do direct deals with players which can move the needle (more scale)
  • if markets get too consolidated Google can always launch a vertical service & tip the scale back in the other direction (I see your Amazon ad revenue and I raise you free product listing ads, aggregated third party reviews, in-SERP product comparison features, and a "People Also Ask" unit)
  • the macroparasites have more "sameness" between them (making it easier for Google to create a competitive clone or copy)

So long as Google maintains a monopoly on web search the bias toward macroparasites works for them. It gives Google the outsized margins which ensures healthy Alphabet profit margins even if the median of Google's 156,000+ employees pulls down nearly $300,000 a year. People can not see what has no distribution, people do not know what exist in invisibility, nor do they know which innovations were held back and what does not exist due to the current incentive structures in our monopoly-controlled publishing ecosystem.

I think when people complain about the web being inauthentic what they are really complaining about is the algorithmic choices & publishing shifts that did away with the indy blogs and replaced them with the dopamine feed viral tricks and the same big box scaled players which operate multiple parallel sites to where you are getting the same machinery and content production house behind multiple consecutive listings. They are complaining about the efforts to snuff out the microparasite also scrubbing away personality, joy, love, quirkiness, weirdness, and the zany stuff you would not typically find on content by factory order websites.

Let's Go With Consensus Here!

The above leads you down well worn paths, rather than the magic of serendipity & a personality worn on your sleeve that turns some people on while turning other people off.

Text which is roughly aligned with a backward looking consensus rather than at the forefront of a field.

History is written by the victors. Consensus is politically driven, backward looking, and has key messages memory holed.

Some COVID-19 Fun to "Fact" Check

I spent new years in China before the COVID-19 crisis hit & got sick when I got back. I used so much caffeine the day I moved over a half dozen computers between office buildings while sick. I week later when news on Twitter started leaking of the COVID-19 crisis hit I thought wow this looks even worse than what I just had. In the fullness of time I think I had it before it was a crisis. Everyone in my family got sick and multiple people from the office. Then that COVID-19 crisis news came out & only later when it was showed that comorbidities and the elderly had the worse outcomes did I realize they were likely the same. Then after the crisis had been announced someone else from the office building I was in got it & then one day it was illegal to go into the office. The lockdown where I lived was longer than the original lockdown in Wuhan. Those lockdowns destroyed millions of lives.

The reason the response to the COVID-19 virus was so extreme was huge parts of politically interested parties wanted to stop at nothing to see orange man ejected from the White House. So early on when he blocked flights from China you had prominent people in political circles calling him xenophobic, and then the head of public health in New York City was telling you it was safe to ride the subway and go about your ordinary daily life. That turned out to be deadly partisan hackery & ignorance pitched as enlightenment, leading to her resignation.

Then the virus spreads wildly as one would expect it to. And draconian lockdowns to tank the economy to ensure orange man was gone, mail in voting was widespread, and the election was secured.

Some of the most ridiculous heroes during this period wrote books about being a hero. Andrew "killer" Cuomo had time to write his "did you ever know that I'm your hero" book while he simultaneously ordered senior living homes to take in COVID-19 positive patients. Due to fecal-oral transmission and poor health outcomes for senior citizens sick enough to be in a senior living home his policies lead to the manslaughter of thousands of senior citizens.

You couldn't go to a funeral and say goodbye because you might kill someone else's grandma, but if you were marching for social justice (and ONLY social justice) that stuff was immune to the virus.

Suggesting looking at the root problems like no dad in the home is considered sexist, racist, or both. Meanwhile social justice organizations champion tearing down the nuclear family in spite of the fact that if you tear down the family all you are left with is the collective AND "mandatory collectivism has ended in misery wherever it’s been tried."

Of course the social justice stuff embeds the false narrative of victimhood, which then turns many of the fake victims into monsters who destroy the lives of others - but we are all in this together.

Absolutely nobody could have predicted the rise of murder & violent crime as we emptied the prisons & decriminalized large swaths of the penal code. Plus since many crimes are repeatedly ignored people stop reporting lesser crimes, so the New York Times can tell you not to worry overall crime is down.

In Seattle if someone rapes you the police probably won't even take a report to investigate it unless (in some cases?) you are a child. What are police protecting society from if rape is a freebie that doesn't really matter? Why pay taxes or have government at all?

What Google Wants

The above sidebar is the sort of content Google would not want to rank in their search results. :D

They want to rank text which is perhaps factually correct (even if it intentionally omits the sort of stuff included above), and maybe even current and informed, but done in such a way where you do not feel you know the author the way you might think you do if you read a great novel. Or hard biased content which purports to support some view and narrative, but is ultimately all just an act, where everything which could be of substance is ultimately subsumed by sales & marketing.

The Market for Something to Believe In is Infinite

Each re-representation mash-up of content in the search results decontextualizes the in-depth experience & passion we crave. Each same "big box" content factory where a backed entity can withstand algorithmic volatility & buy up other publishers to carry learnings across to establish (and monetize) a consensus creates more of a bland sameness.

That barrier to entry & bland sameness is likely part of the reason the recent growth of Substack, which sort of acts just like a blog did 15 or 20 years ago - you go direct to the source without all the layers of intermediaries & dumbing down you get as a side effect of the scaled & polished publishing process.

Automating Ourselves Out of Existence

Time has grown more scarce after having a child, so I rarely blog anymore. Though I thought it probably made sense to make at least a quarterly(ish) post so people know I still exist.

One of the big things I have been noticing over the past year or so is an increasing level of automation in ways that are not particularly brilliant. :D

Just from this past week I've had 3 treat encounters on this front.

One marketplace closed my account after I made a bunch of big purchases, likely presuming the purchases were fraudulent based on the volume, new account & an IP address in an emerging market economy. I never asked for a refund or anything like that, but when I believe in something I usually push pretty hard, so I bought a lot. What was dumb about that is they took a person who would have been a whale client & a person they were repeatedly targeting with ads & turned them into a person who would not recommend them ... after being a paying client who spent a lot and had zero specific customer interactions or requests ... an all profit margin client who spent big and then they discarded. Dumb.

Similarly one ad network had my account automatically closed after I had not used it for a while. When I went to reactivate it the person in customer support told me it would be easier to just create a new account as reactivating it would take a half week or more. I said ok, went to set up a new account, and it was auto-banned and they did not disclose why. I asked feedback as to why and they said that they could not offer any but it was permanent and lifetime.

A few months go by and I wondered what was up with that and I logged into my inactive account & set up a subaccount and it worked right away. Weird. But then even there they offer automated suggestions and feedback on improving your account performance and some of them were just not rooted in fact. Worse yet, if they set the default targeting options to overly broad it can cause account issues in a country like Vietnam to where if you click to approve (or even auto approve!) their automated suggestions you then get notifications about how you are violating some sort of ToS or guidelines ... if they can run that logic *after* you activate *their* suggestions, why wouldn't they instead run that logic earlier? How well do they think you will trust & believe in their automated optimization tips if after you follow them you get warning pop overs?

Another big bonus recently was a client was mentioned in a stray spam email. The email wasn't from the client or me, but the fact that a random page on their site was mentioned in a stray spoofed email that got flagged as spam meant that when the ticket notification from the host sent wounded up in spam they never saw it and then the host simply took their site offline. Based on a single email sent from some other server.

Upon calling the host with a friendly WTF they explained to the customer that they had so many customers they have to automate everything. At the same time when it came time to restoring hosting that the client was paying for they suggested the client boot in secure mode, run Apache commands x and y, etc. ... even though they knew the problem was not with the server, but an overmalicious automated response to a stray mention in a singular spam email sent by some third party.

When the host tried to explain that they "have to" automate everything because they have so many customers the customer quickly cut them off with "No, that is a business choice. You could charge different prices or choose to reach out to people who have spent tens of thousands on hosting and have not had any issues in years." He also mentioned how emails can be sent to spam, or be sent to an inbox on the very web host that went offline & was then inaccessible. Then the lovely customer support person stated "I have heard that complaint before" meaning they are aware of the issue, but do not see it as an issue for them. When the customer said they should follow up any emails with an SMS for servers going offline the person said you could do it on your end & then later sent them a 14-page guide for how to integrate the Twillio API.

Nothing in the world is fair. Nothing in the world is equal. But there are smart ways to run a business & dumb ways to run a business.

If you have enough time to write a 14-page integration guide it probably makes sense to just incorporate the feature into the service so the guide is unneeded!

Businesses should treat their heavy spenders or customers with a long history of a clean account with more care than a newly opened account. I had a big hedge fund as a client who would sometimes want rush work done & would do stuff like "hey good job there, throw in an extra $10,000 for yourself as a bonus" on the calls. Whenever they called or emailed they got a quick response. :D

I sort of get that one small marketplace presuming my purchases might have been a scam based on how many I did, how new my account was, and how small they were, but the hosting companies & ad networks that are worth 9 to 12 figures should generally do a bit better. Though in many ways the market cap is a sign the entity is insulated from market pressures & can automate away customer service hoping that their existing base is big enough to offset the customer support horror stories that undermine their brand.

It works.

At least for a while.

A parallel to the above is my Facebook ad account, which was closed about a half decade or so ago due to geographic mismatch. That got removed, but then sort of only half way. If I go to run ads it says that I can't, but then if I go to request an account review to once again explain the geographic difference I can't even get the form to submit unless I edit the HTML of the page on the fly to seed the correct data into the form field as by default it says I can not request a review since I have no ad account.

The flip side of the above is if that level of automation can torch existing paid accounts you have to expect the big data search & social companies are taking a rather skeptical view of new sites or players wanting to rank freely in their organic search results or social feeds. With that being the case, it helps to seed what you can to provide many signals that may remove some of the risks of getting set in the bad pile.

I have seen loads of people have their YouTube or Facebook or whatever such account get torched & only override the automated technocratic persona non grata policies by having followers in another channel who shared their dire situation so it could get flagged for human review and restoration. If that happens to established & widely followed players who have spent years investing into a platform the odds of it happening to most newer sites & players is quite high.

You can play it safe and never say anything interesting, ensuring you are well within the Overtone Window in all aspects of life. That though also almost certainly guarantees failure as it is hard to catch up or build momentum if your defining attribute is being a conformist.

Engineering Search Outcomes

Kent Walker promotes public policies which advantage the Google monopoly.

His role doing that means he has to write some really bad hot takes that lack context or intentionally & dishonestly redirect attention away from core issues - that's his job.

With that in mind, his most recent blog post defending the Google monopoly was exceptional.

Force Ranking of Inferior Search Results

"When you have an urgent question — like “stroke symptoms” — Google Search could be barred from giving you immediate and clear information, and instead be required to direct you to a mix of low quality results."

On some search queries users get a wall of Google ads, the forced ranked Google insert (or sometimes multiple of them with local & ecommerce) and then there can even be a "people also ask" box above the first organic result.

The idea that organic results must be low quality if not owned & operated indicates 1 of the following 3 must be true:

  • they should not be in search
  • their content scraping & various revenue shifting scams with their ad tech stack demonetized legit publishers
  • their forced rank of their own content is stripping them of the signals needed to rank websites & pages

Whenever Google puts a "people also ask" box above the first organic result that is them saying they did not know what to rank, or they are just trying to create a visual block to push the organic result set down the page and user attention back up toward the ads.

The solution to Google's claims is easy to solve. Either of the following would work.

  • Have an API that allows user choice (to set rich snippet or vertical defaults in various categories), or
  • If the vertical inserts remain Google-only then for Google to justify force ranking their own results above the organic result set Google should also be required to rank those same results above all of their ads, so that Google is demonetizing Google along with the rest of the ecosystem, rather than just demonetizing third parties.

If the thesis that this information needs to be front and center & that is a matter of life or death, then asking searchers to first scroll past a page or two of ads is not particularly legitimate.

Spam & Security

"when you use Google Search or Google Play, we might have to give equal prominence to a raft of spammy and low-quality services."

Many of the worst versions of spam that have repeatedly made news headlines like fake tech support, fake government document providers, and fake locksmiths were buying distribution through Google Ads or were featured in the search results through Google force ranking their own local search offering even though they knew the results were vastly inferior to Yelp.

If Google did not force rank Google local results above the rest of the organic result set then the fake locksmiths would not have ranked.

I have lost count of how many articles I have read about hundreds or thousands of fake apps in the Google Play store which existed to defraud advertisers or commit identity theft, but there have been literally thousands of such articles. I see a similar headline at least once a month without eve looking for them. Here is one this week for scammers monetizing the popularity of Wordle with fake apps.

Making matters worse, some of the tech support scams showed the URL of a real business and rerouted the call through a Google number directly to a scammer. A searcher who trusted Google & sees or on Google Ads in the search results then got connected with a scammer who would commit identity theft or encrypt their computer then demand ransom cryptocurrency payments to decrypt it.

After making the ads harder to run for scammers Google decided the problem was too hard & expensive to sort out so they also blocked legitimate computer repair shops.

Sometimes Google considers something spam strictly due to financial considerations.

Their old remote rater documents stated *HELPFUL* hotel affiliate websites should be labeled as spam.

Years later the big OTAs are complaining about Google eating their lunch as well as Google is twice as big as the next player.

At one point Google got busted for helping an advertiser route around the automated safety features built into their ad network so that they could pay Google to run ads promoting illegal steroids.

With cartels, you can only buy illegal goods and services from the cartel if you don't want to suffer ill consequences. The same appears to be true here.

The China Problem

"Handicapping America’s technology leaders would threaten our leading sources of research and development spending — just as bipartisan voices in Congress are recognizing the need to increase American R&D investment to stay competitive in the global race for AI, quantum, and other advanced technologies."

We are patriotic, and, but China... is a favorite misdirection of a tech monopolist.

The problem with that is while Eric Schmidt warns it is a national emergency if China overtakes the US in AI tech, Google also operates an AI tech lab in China.

In other words, Eric Schmidt is trying to warn you about himself and his business interests at Google.

Duplicitous? Absolutely.

Patriotic? Less than Chamath!


"the online services targeted by these bills have reduced prices; these bills say nothing about sectors where prices have actually been rising and contributing to inflation."

Technology is no doubt deflationary (moving bits on an optical line is cheaper than printing out a book and shipping it across the world) BUT some dominant channels have increased the cost of distribution by increasing the chunk size of information and withholding performance information.

Before Google Analytics was "free" there was a rich and vibrant set of competition in web analytics software with lots of innovation from players like ClickTracks.

Most competing solutions went away.

Google moved away from an installed licensing model to a hosted service where they can change the price upon contract renewal.

Search hid progressively more performance information over time, only sampled data from larger data sets, & now you can sign up for Google Analytics 360 starting at only $150,000 per year.

The hidden search performance data also has many layers to that onion. Not only does Google not show keyword referrers on organic search, but they often don't show your paid search keywords either, and they keep extending out keyword targeting broader than advertisers intend.

Google used to pay Brad Geddes to run official Google AdWords ad training seminars for advertisers, so the idea that *he* has to express his frustrations on Twitter is an indication of how little effort Google is putting into having open communications channels or caring about what their advertisers think.

This is in accordance with the Google customer service philosophy:

he told her that the whole idea of customer support was ridiculous. Rather than assuming the unscalable task of answering users one by one, Page said, Google should enable users to answer one another's questions.

Those who were paying for ads get the above "serve yourself" treatment, all the while Google regularly resets user default ad settings to extend out ad distribution, automatically ad keywords, shift to enhanced AdWords ad campaigns, etc.

Then there are other features which would be beneficial and offered in a competitive market that have been deprioritized. Many years ago eBay did a study which showed their branded Google AdWords ad buys were cannibalistic to eBay profits. Google maintained most advertisers could not conduct such a study because it would be too expensive and Google does not make the feature set available as part of their ad suite.

Missing Information

"When you search for local businesses, Google Search and Maps may be prohibited from highlighting information we gather about hours of operation, contact information, and reviews. That could hurt small businesses and local retailers, as well as their customers."

Claiming reviews or an attempt to offer a comprehensive set of accurate review data as a strong point would be economical with the truth.

Back when I had a local business page my only review was from a locksmith spammer / scammer who praised his own two businesses, trashed a dozen other local locksmiths, crapped on a couple local SEO services, and joked about how a local mover smashed the guts out of his dog. Scammer fake reviewer's name was rather sophisticated ... it was ... Loop Dee Loop

About a decade back when Google was clearly losing Google took Yelp reviews wholesale (sometimes without even attributing them to Yelp!) and told Yelp that if they did not want Google stealing their work and displacing them with a copy of it then they should block GoogleBot. Google offered the same sort of advice / threat to TripAdvisor.

A few years before that Google temporarily "forgot" to show phone numbers on local listings.

After Yelp turned down an acquisition offer by Google & Yelp did a great job making some people aware of how Google was stealing their reviews wholesale without attribution Google bought Zagat & Fromer's to augment the Google local review data and then sold those businesses off.

This is sort of the same playbook Google has run in the past elsewhere. After Groupon said no to Google's acquisition offer, Google quickly provided daily deal ads to over a dozen Groupon competitors to help commoditize the Groupon offering and market position.

Ultimately with the above sort of stuff Google is primarily a volume aggregator or has lower editorial costs than pure plays due to the ability to force bundle their own distribution. And they use the ability to rank themselves above a neutral algorithmic position as a core part of their biz dev strategy. When shopping search engines were popular Google kept rewording the question set they sent remote raters to justify rank demotion for shopping search engines & Google also came up with innovative ranking "signals" like concurrent ranking of their own vertical search offering whenever competitors x or y are shown in the result set & rolled out a "diversity" algorithm to limit how many comparison shopping sites could appear in the search results. The intent of the change was strictly anti-competitive:

"Although Google originally sought to demote all comparison shopping websites, after Google raters provided negative feedback to such a widespread demotion, Google implemented the current iteration of its so-called 'diversity' algorithm."

As a matter of fact, part of one of many document dumps in recent years went further than the old concurrent ranking signal to a rank x above y feature which highlights how YouTube can be hard coded at a number 1 ranking position.

Part of that guide highlighted how to hardcode ranking YouTube #1.

If you re-represent content & can force rank yourself #1 (with larger listings) that can be used to force other players onto your platform on your terms. Back when YouTube was must less of a sure thing Google suggested they could threaten to change copyright.

This same approach to "relevancy" is everywhere.

Did you watermark your images? Well shame on you, as that is good for a rank demotion

And if there are photos which are deemed illegal Google will make you file an endless series of DMCA removal requests even though they already had the image fingerprinted.

Now there are some issues where there is missing information. These areas involve original reporting on local politics & are called news deserts. As the ad pie has consolidated around Google & Facebook that has left many newspapers high and dry.

Private equity players like Alden Global Capital buy up newspapers, fire journalists, and monetize brand equity as they drive the papers into the ground.

If you are sub-scale maybe Google steals your money or hits you with a false positive algorithm flag that has you seeking professional mental health help.

Big players get a slower blood letting.

Google has maintained they do not make any money from news search, but the states lawsuit around ad tech made it clear Google promoted AMP for anti-competitive purposes to block header bidding, lied to news publishers to get them to adopt AMP and eat the tech costs of implementation, did a deal with their biggest competitor in online advertising Facebook to maintain the status quo, charge over double what their competitors do for ad tech, and had a variety of bid rigging auction manipulation algorithms they used to keep funneling more money to themselves.

Internally they had an OKR to make *most* search clicks land on AMP pages within a year of launch

"AMP launched as an open source project in October 2015, with 26 publishers and over 40 publications already publishing AMP files for our preview demo. Our team built and is now racing towards launching it for all of our users. We're responsible for the AMP @ Google integrations, particularly focusing on Search, our most visible product. We have a Google-wide 2016 OKR to deliver! By the end of 2016, our goal is that 50%+ of content consumed through Search is being consumed through AMP."

You don't get over half the web to shift to a proprietary version of HTML in under a year without a lot of manipulation. Review

Background / Intro

One of my longtime friends who was Internet marketing long before I was hit me up on Skype about a week ago praising I have to think long and hard about any other time he has really pitched or recommended something like that & really I just can't think of any other time where he did that. The following day my wife Giovanna mentioned something to me and I was like "oh you should check out this thing my buddy recommended yesterday" and then I looked and realized they were both talking about the same thing. :D

I have a general heuristic that if people I trust recommend things I put them near the top of the "to do" list and if multiple people I trust do that I pull out the credit card and run at it.

Unfortunately I have been a bit burned out recently and launched a new site which I have put a few hundred hours into, so I haven't had the time to do too much testing, BUT I have a writer who works for me who has a master's degree in writing, and figured she could do a solid review. And she did. :D

She is maybe even a bit more cynical than I am (is that even possible?) and a certified cat lady who loves writing, reading, poetry and is more into a soft sell versus aggressive sales.

Full disclosure...the above link and the one at the end of this post are affiliate links, but they had zero impact on the shape or format of the review. The reviewer was completely disconnected from the affiliate program and I pulled out my credit card to pay for the software for her to test it out.

With that tiny bit of a micro-introduction, the rest of the post from here on out is hers. I may have made a couple minor edits for clarity (and probably introduced a few errors she will choke me for. :D) but otherwise the rest of this post is all her ...

An In-depth Review of the Writing Software

Considering the possibilities of artificial intelligence (AI), we picture robots doing tasks autonomously like humans. With a computer’s brain power, productivity is accelerated significantly. We also expect AI programs to have the capability to evolve intelligently the longer they are used. These types of AI employ “machine learning,” or deep learning to solve problems.

AI technology can be leveraged by various industries, especially with writing. Recently, I learned about the copywriting tool. It uses machine learning which claims to write “high converting copy” for websites, ads, landing pages, emails, etc. The software is geared towards writers, marketers, entrepreneurs, and agencies that benefit from creating engaging and effective copy. To date, companies such as Hubspot, Shopify, and Salesforce are known to use the software. Currently, it’s offering a 7-day free trial with 20,000-word credits.

To give you the lowdown on, I wrote an in-depth review of how this software works. I’ll go through its various features and show examples of how I used them. I’ll include the advantages of using’s Jasper (that’s what it’s called) in writing scenarios. More importantly, I’ll discuss challenges and specific limitations this tool might present.

Assistance in Creating High Conversion Copy

As a writer doing web copy for 10 years, including the time I took a post-grad creative writing degree, I grabbed the opportunity to try this AI software. For starters, it struck me how claims to provide “high converting copy” for increased conversion and higher ROI. Such claims are a tall order. If you’ve been in the marketing or sales industry, you’d know conversion depends on so many other factors, such as the quality of the actual product, customer support, price, etc. It’s not just how well copy is written, though it’s a vital part. But anyway, upon more research, I learned the app generates copy based on proven high conversion sales and marketing messages.

To be honest, I have mixed feelings about this conversion strategy. I believe it’s a double-edged sword. This is not to undermine facts or measurable data. Basing content creation on “proven content” means you’re likely using the same phrases, techniques, and styles already used by successful competitors. This serves as a jumping board for ideas of course, so you know what’s already there. However, it can be an echo chamber. Marketers must not forget that execution must still be fresh. Otherwise, you’ll sound like everyone else.

Next, while it seems sustainable, it also sounds pretty safe. If your product or service is not that distinct, you must put extra effort to create content that stands out. This applies to all aspects of the marketing strategy, not just in writing content. It’s a crucial principal I learned after reading Purple Cow by Seth Godin (thanks for the book suggestion, Aaron!).

Depending on your product or service, will generate copy that most consumers keep going back to. Based on the samples it generated, I’d say it really does come up with engaging copy, though it needs editing. If your business must rewrite product descriptions for extensive inventories, can cut the time in half. It can help automate description rewriting without hiring more writers. That saves money and time, so businesses need fewer writers and editors.

What did I learn? can make writing and editing faster, yes, especially for low-level content focused on descriptions. It can also inform the strength of your ideas for more creative campaigns. However, it still takes solid direction and creativity to drive good marketing copy forward. That said, it’s only as good as the writer utilizing this app. As a content creator, you cannot rely on it solely for creativity. But as an enhancer, it will significantly help push ideas forward, organize campaigns, and structure engaging copy effectively.

When you use this app, it offers many different features that help create and organize content. It also customizes copy for various media platforms. Beyond rewriting , it even has special brainstorming tools designed to help writers consider various idea angles. This can add more flavor and uniqueness into a campaign.

At the end of the day, what will set your copy apart is the strength of your ideas and your communication strategy. How you customize content for a business is still entirely up to you. AI writing tools like can only help enhance your content and the ideas behind it. It’s a far cry from creating truly unique concepts for your campaign, but it definitely helps. Writing Features & How They Work

This AI writing app comes with plenty of “writing templates” that are customized to help you write with a specific framework or media platform in mind. Currently, offers 39 different writing templates or content building blocks that deliver results. We’ll provide details for how each one works.

For company or product descriptions, has a Start Here step by step guide, which says users should alternate between the Product Description and the Content Improver template until they have found the right mix they’re looking for. But for this review, I just focused on how to use the templates for different writing projects. The app comes with video instructions as well as a live training call if you need further assistance on how to use it.

Each template asks you to input a description or what you want to write about. This is limited to 600 characters. Writing the description is the sole basis for how Jasper will generate ways to write or expand your content. It also helps you brainstorm and structure ideas for an article or campaign.

But as an issue, I find the 600-character limit can hinder reposting the full content generated by the AI back into the template for improvement. Yes, it churns out marketing copy of more than 600 characters. If you want to post the improved copy again, you might have to do this in two batches. In any case, Jasper can generate as many improved writing samples as you need.

To give you a better idea, here are different templates and how they work. This is going to take a while, so have your coffee ready.

Long-form Assistant

This is for longer articles, emails, scripts, and stories. It’s also suggested for writing books. It has two modes, a blank document where you can start typing freely and an assistant workflow. The blank document also lets you access the rest of the other writing templates vertically. On the other hand, the long-form assistant workflow is where the app asks you to describe the content you want to create. Consider this carefully. The better you can articulate your topic, the higher quality content Jasper can help generate.

For the example, suppose I want to write about what it took to finally release Zack Synder’s 2021 Justice League. I want to write this feature article for my film and culture website.

Jasper asks for a maximum of three keywords. It’s optional, but I presume adding keywords will help Jasper generate more relevant content. Next, it prompts you to write a working title and start an introductory paragraph. Once you write your initial title, it will generate other title ideas.

For the title, I wrote: The Challenges of Releasing Zach Snyder’s Justice League 2021
It generated the following suggestions:

Jasper generated a long list of appropriate and catchy titles. I personally liked “The Tumultuous Journey of Zack Snyder’s Justice League 2021,” though I’d shorten it a bit. I also liked “The Darkest, Toughest Production in Film History,” which basically tells audiences how hard it was to produce the version of the film. Though it’s an exaggeration, it can be qualified in the article. The other suggestions with “Behind the Scenes” and “Towards a Better Script” were more specific angles. I like that I could explore those topics too. Generally, I think it’s definitely a great tool to make title writing faster.

So far, so good, right? But when I got to content suggestions, it got a bit messy. It was mainly because the suggested content was too general. It also tended toward suggesting expansions that were incoherent to the main topic. This did not sound very promising. Moreover, the AI added bits of information such as dates and other related information. I had to check if these details were used accurately. In a previous test I did (and even for this example), it completely got a date wrong. So I advise writers to always double check the details suggested by Jasper.

Take a look below. The top paragraph was the one I wrote, while the ones below are suggested by Jasper.

Content suggestions from Jasper:

1) You might not be able to see Zack Snyder’s Justice League on the big screen, but you can catch it online in 2021. It was released digitally by Warner Bros. on November 27th 2020 and we’ve been watching it slowly climb the ranks of IMDB since then. The film had a troubled production between 2016 and 2017 with the script going through major changes before and during shooting. But now that all is said and done, what did people think? Let’s find out!

2) Justice League is a film that was released on November 17, 2017. The movie had been preceded by Batman v Superman: Dawn of Justice and Wonder Woman. It’s also the fifth installment in the DC Extended Universe (DCEU). Despite being generally well-received by critics, it was considered to be a disappointment at the box office. In this blog post, we’ll take you behind the scenes and show you what went wrong with Zack Snyder’s 2021 Justice League film production!

3) Director Zack Snyder’s Justice League film was one of the most anticipated films of 2017. Unfortunately, the film had a troubled production and was not released until 2021. That didn’t stop it from becoming one of the highest-grossing films of all time. What does this have to do with SEO? When you release content on your website, be sure to include keywords that are relevant to your business and industry!

At first glance, the introduction actually looks appealing to Justice League fans. Many people have been anticipating it on the big screen. But upon further reading, compared to the paragraph I wrote, the AI content had so many problems. Besides being too general, it had issues with imprecise details. Though you can argue these problems are small and editable, it adds time to your work. It can even derail you from focusing on your topic.

The first AI suggestion wrote that Snyder Cut was released digitally by Warner Bros. in November 27, 2020. Upon further research, I found no such confirmation of this. However, there was a YouTube video “speculating” it’s release in November 2020. But from the looks of it, this did not pan out. Officially, Zack Snyder’s Justice League was released in March 18, 2021 by HBO Max via streaming platform, according to Rotten Tomatoes. And yes, it has been climbing the ranks since its digital release.

If you’re not careful about fact-checking, you might end up with misleading information. And frankly, I feel as if some of the other suggestions may tend towards fluff. However, what you can do is choose the best suggestions and put them together into one coherent paragraph. The first suggestion ended the introduction with “But now that all is said and done, what did people think? Let’s find out!” While it’s something I want to touch on eventually, it is not the main focus of my introduction. The AI was not sensitive enough to sense this follow up was out of place. I’d rather get to the details of the challenging production. If I use this suggestion, I’ll have to edit it into “Let’s take a look at what it took to deliver the highly anticipated Snyder Cut,” or something to that effect.

The second example, on the other hand, was quite a miss. It started by talking about the 2017 Justice League film. While it’s good to expound on the history of the project started, it got lost in discussing the 2017 version. Worse, it did not transition the topic smoothly into the 2021 Snyder Cut. If I read this introduction, I’d be confused into thinking the article was about the 2017 Justice League. Finally, it awkwardly ended the paragraph with “we’ll take you behind the scenes and show you what went wrong with Zack Snyder’s 2021 Justice League film production!” Besides the wordy sentence, suddenly it’s talking about the 2021 Justice League out of nowhere. I would not phrase the production’s challenges as something that went wrong. That’s unnecessary hype. It’s confusing, and just an example of bad writing. Again, while it can be fixed with editing, I feel better off writing on my own.

Finally, the third example actually started okay. But then it started talking about SEO out of nowhere. I don’t know where that came from or why the AI did that, but I’ll count it as a totally unusable suggestion from the app. I reckon there might be more of those glitches if I generate more content suggestions from Jasper.


I noticed these were nuances the AI was not able to catch. It’s probably even based on trending articles at the time, which had a tendency towards hype and dated showbiz information. And though the suggestions were interesting, they were mostly too general or against the direction I needed. If the usage of the information is not accurate, imagine what that would mean for health or political articles. But too be fair, it did generate other usable suggestions with less serious edits. It’s worth looking into those.

However, by this time, I felt I was better off writing the feature without the app, at least for this example. I guess it’s really a hit or miss. Even with so many content suggestions, I think you can still end up with inappropriate samples even if you find good ones. But at least you got a good title already. Personally, I’d rather go straight to researching on my own.

Framework Templates allows you to write copy based on marketing frameworks that have been used by professionals for years. It’s ideal for brands, products, and services you need to promote. This features includes the following templates:

  • AIDA Framework: The AIDA template stands for Attention, Interest, Desire, and Action. This basically divides your copy into sections drawing attention from consumers and piquing their interest. The suggested copy also includes content that appeals to the consumer’s desire, then ends with a call to action.
  • PAS Framework: The PAS template is structured by generating copy which highlights the consumer’s Problem, Agitate, and Solution. It’s focused on how a particular product will help solve a consumer’s problem.
  • Bridge-After-Bridge Framework: Also known as BAB framework, this copywriting structure revolves around the idea of getting a consumer from a bad place to a better one. It shows the before and after scenario after benefitting from a product.

For this example, I used the AIDA template for an imagined non-invasive weight loss service company. The new company promotes fitness and advocates against fad diets. It performs non-surgical weight loss procedures, such as wraps and thermomagnetic massages.

Again, Jasper asks for a description. It also requires you to specify the tone of the copy. I placed “friendly” and “professional” under the box. See my input below.

Here’s the first suggestion from Jasper:

Based on this example, I’d say the AI-generated content is quite engaging. It tried to have a personal touch by letting the customer know they’re here to help. The writing empathizes with consumers who have a hard time losing weight. However, since this is for a new company, the introduction “We have helped thousands of people lose weight and get in shape,” does not apply. So as a writer, I simply have to remove it. This can be replaced with the intent to help more people lose weight and get in shape.

I actually pulled out at least 6 different content suggestions. From these, writers could get the best parts and edit them into one strong copy description. On it’s own, the content would still benefit from a lot of editing. Here are some issues you might encounter while generating copy suggestions:

  • Hard Sell Copy. The sample content can be hard sell, even if you specify a professional tone of voice. It tends to use exclamation marks (!) per sample. I believe this depends on the product or service you are writing about. Certain products or services may sell more with the hard sell approach, so the AI suggests this strategy. It may also appear like the “proven” way to communicate to consumers. But if you’re going against this direction, it’s a nuance the AI tool might miss. If your business or client specifically avoids exclamation marks your copy, be ready to make the necessary edits.
  • Can be Wordy, Long, Redundant. In terms of style, here’s where you can’t rely on Jasper to write the entire thing. If you happen to input a long and detailed product description, the AI has a tendency to generate wordy variations of the copy. If you notice, some details are also redundant. In copywriting standards, this needs tightening. Conciseness can be an issue, most notably if you’re not used to brevity. Thus, I believe this tool will best benefit writers and editors who have considerable experience in crafting straightforward copy.

Product Description

The app comes with a special template for creating product descriptions. If you have a large inventory of product information for rewriting, this is the right tool to use. It even comes with an optional language output translation feature, which is available in other templates too.

However, the language feature is limited. I tried putting Thai, Italian, and Japanese and it generated few suggestions, some mixed with English. Same thing with Punjabi and Vietnamese. In other templates, they just keep making English suggestions. Filipino is also not recognized by the AI, which likely means it cannot translate a bunch of other languages. This feature obviously needs development. But it’s not the main feature, so I doubt they’ll do a lot of improvements.

For this example, I used an imagined tire center that offers products and services throughout the U.S. I specifically wrote that it’s the second most affordable tire center in the country. I asked for a professional and witty tone. I’m not at all fluent in Spanish, but I placed Spanish under the output language box.

Below is the first suggested copy in Spanish:

When translated through Google, it reads:

“Don’t think twice, Adam’s Tire Center is your best option because it offers the largest range of products for cars and wagons. Join our satisfied customers and insure your tires with the Road Hazard Warranty service. Call or visit our sales center in Miami, FL, where we are honored to help you.”

Obviously, I can’t comment much on the accuracy of the translation. Though certainly, I have doubts for how writing in another language can capture certain styles and tones. But right now, what I’m more concerned with is the tendency to use superlative descriptions that might not accurately fit the brand. Things like “we offer the largest range of products” should probably be tweaked to “we offer a wide range of products…” If your tire center does not offer the largest inventory, you should not be writing that. It also assumed a specific location, which prompts the writer to include the actual business location (this is a good suggestion). Again, the AI copy would benefit from fine-tuning to make it specific to your product or service.

Now, back to English. Here are three other content samples generated by Jasper:

The English AI-generated samples are not so bad. But in the last sample, there is a tendency for hard sell terms like “unmatched in quality,” that you need to watch out for. You can get the best parts and put them into one solid brand description. But again, these tend to be wordy and long. It would help to use the Hemingway app or Grammarly to make the descriptions tight and concise.

Content Improver

Using the Content Improver template will help you tweak the product or service descriptions you came up with. To show you how it works, I placed the content I wrote based on the edited tire center descriptions Jasper generated.

For this example, I placed professional and witty under tone of voice.

Suggested content from Jasper:

Based on the sample suggestion, I’d say the first two can pretty much stand on their own. These are straightforward copies that address consumer needs with a direct call to action. Though the first one may sound a bit informal, it might fit the type of consumer demographic you are targeting. Finally, the last example gets a bit wordy but can be fixed with a couple of edits. The major issue is the number (555-5555), which the AI mistook for an address.

Marketing Angles

Besides churning out copy suggestions, has a brainstorming tool. This basically takes your product or service and comes up with various campaign ideas to promote it. If you’re running out of concepts for promotion, Jasper leverages on your product’s features and strengths. I appreciate that it tried to come up with benefit-driven copy based on the example I put.

For this example, the product I used is a gym management software. It helps gym owners manage activities, schedules, and handle payments. The software aims to run gyms more efficiently.

I personally find the following suggestions helpful in pushing the strengths of a product. I would definitely use this tool for brainstorming ideas. Here’s what Jasper generated:

Unique Value Propositions

Another intriguing feature is the unique value propositions (UVP ) template. UVP is essentially a clear statement that describes the benefit your product offers. It also captures how you address your customer’s needs and what distinguishes you from the competition.

If you have a product or service, It claims to generate copy that describes your product’s unique advantage in a remarkable way. To test how this works, I used the previous example, which is the gym software. It came up with several statements that emphasized the product’s benefits. See Jasper’s suggestions below. Personally, I like the idea of software that helps me make more money with less work.

Feature Benefit

The feature benefit template comes up with a list of advantages offered by your product. For this example, the product is a camisole for plus size women. You’ll see how it took the paragraph details and made bulleted benefits based on those features. It’s a useful tool if you want to break down your product’s unique selling points so you can further emphasize them in your campaign.

Persuasive Bullet Points

Another related function is the persuasive bullet points template. This is very similar to the feature benefit template. Personally, I think it’s either you use this or the feature benefit template if you want to highlight product advantages in bullet points. On the other hand, this template doesn’t categorize benefits as emotional or standard advantages.

Copy Headline and Sub-headline Templates also comes with copy headline and sub-headline templates. They claim the AI is “trained with formulas from the world’s best copywriters.” It also guaranteed to create “high-converting headlines” for businesses. At this point, the only way to know if it does have high conversion is to see actual results. Right now, my review can’t prove any of that. But it would be interesting to know from companies who have been using this software for results.

  • Perfect Headline: For this template, I used an earlier example that provides non-invasive weight loss services. You’ll see the product description I used, followed by the suggestions made by Jasper. I specifically liked the headline: Science-based approach to safe, effective fat loss. It’s right concept I was going for.

  • Website Sub-headline: I used the same product description for the sub-headline. I also used the suggested headline generated by Jasper, which is “Science-based approach to safe, effective fat loss.” Based on Jasper’s suggestions, I liked the last one, which emphasizes non-invasive slimming. It also tells consumers the procedure is safe. Though it tends to be wordy, I appreciate it provides different ways you can get your message across.

Sentence Expander

Another interesting feature is the sentence expander. It claims to make your sentence longer and more creative. I guess it should help you get to another thought if you caught writer’s block. But I’m wary what kind of suggestions it might give. When I tried it, it’s just another way to rewrite your sentence in a longer, more detailed way.

In any case, see my sentence below.

Here’s what Jasper generated:

I’m actually not a fan of long-winded sentences. However, I do appreciate the extra details added by the AI. I can use these suggestions if I make further edits on them. But realistically, if I’m writing an article, I’d skip this and go directly to what I’m trying to say. That would save me time. If I want to talk about the negative psychological effects of social distancing, I’d write that point per point. My idea of expansion is moving an argument forward, not merely adding more details to what was already said.

Creative Story

Here’s an interesting template I was curious to try. I wonder how Jasper would develop a two sentence plot. It’s fascinating to see how an AI that uses “proven high conversion data” would suggest story development.

For my example, I took a horror story plot inspired by the Bone Turner from a popular horror podcast called The Magnus Archives. See my plot description and the suggestions made by Jasper.

Story suggestions by Jasper:

I have to say, these are very interesting ideas for an introduction. It’s also funny how it used the name “Jonathon,” because the actual name of main character in the Magnus Archives is “Jonathan.” I kind of think that was on purpose, since the AI probably knows the Bone Turner is from a popular online show.

In any case, I particularly liked the second suggestion. With some editing and fine-tuning, you could fix the details to fit the story in your head. On the other hand, I’m wary authors might rely too much on this to bridge plot gaps. While it’s amusing, it’s more compelling to read plot twists and resolutions that are not forced. At this stage, I’m still not convinced the AI can make a story without contrived plot twists.

Email Subject Lines

Besides creative writing tools, also has templates for email marketing. This feature is made for businesses or individuals who want to promote products and services via email. The app claims to come up with catchy subject lines that draw consumers to open your email. In this example, I used an imaginary cake shop that delivers throughout LA. I thought Jasper came up with a long list of creative subject lines. These were spot on for the example. Since I am a cake person, I’d likely read this kind of email.

Personal and Company Bio

You can also generate creative personal and company bios through Jasper. If you’re running a personal blog or website, Jasper generates personal bios in first person or third person POV, whichever you are more comfortable with. I’m actually pleased with what the AI suggested. It’s a good start, because I find it hard writing about myself.

The example below is not me, of course. I made up Jessica Ackerman as the founder of Mad Cakes in LA.

Here’s what Jasper generated:

It does sound like a personalized bio. Especially with the detail about cuddling with cats and dogs. Again, I’d edit it to be more particular about details. Other than that, I think it’s a good tool to use.

Next, Jasper also generates company bios that sound professional. I put a three-sentence info about a company that boosts website conversion for businesses. I was surprised how long the suggestions were. It also presumed the names of clients the company has serviced (TripAdvisor, Yelp, etc.). Again, for particular information like this, it’s important to edit or remove them. Otherwise, you might publish copy with misleading details.

Suggestions from Jasper:

Real Estate Listing – Residential

You can utilize this template to create creative and descriptive residential listings. It’s helpful for real estate agents and people who are planning to sell their property. The following shows information about a house for sale, followed by listing suggestions by Jasper.

Suggestions from Jasper:

It’s interesting how the suggested content appeals to the consumer’s idea of a perfect home. It tries to paint a picture of affluent living just based on the golf course description I supplied. But again, for accuracy, these added details should be edited by the writer.

Templates for Specific Online Platforms

Besides articles and product or brand descriptions, expect to provide special writing features for online platforms. This includes Facebook, Instagram, YouTube, Google, and Amazon accounts. The AI’s content suggestions are based on posts and ads that have generated high traffic on these platforms. I think this a good tool to use if you want an edge over what already sells.

  • Facebook Ad Headline: Makes catchy headlines for FB ads, claims to increase chances of clicks that lead to sales.
  • Facebook Ad Primary Text: Claims to generate high converting copy for FB ad’s primary text section.

For the Facebook ad headline, my example is a cake shop that delivers a wide assortment of cakes in Los Angeles. It specifically mentions delivering cakes “within an hour or your money back.” Here’s the example and Jasper’s suggested content.

AI ad sample headlines:

I must say these sound like fun and friendly FB headlines. I personally would like a last minute dessert. And if I don’t have time to pick up cake, I’d certainly like one delivered. Just not sure about “Get 500 Instagram Followers,” the suggestion is out-of-place. I’d use this tool for a fresh and exciting FB headline.

Here’s the AI sample for Facebook ad primary text:

Based on the FB text sample, the AI instantly suggested to give away free cake. Most of the generated samples headed toward this direction. It didn’t just generate engaging copy, it likely showed you what other cake shops do to draw more customers. I think it’s a great marketing strategy to have promos and free cake. I also like that it suggested catchy hashtags. But again, I’d fix the wordy and adjective-ridden descriptions. With a little editing, the samples should read more smoothly. Other than that, it’s a fast way to come up with social media copy.

Photo Post Captions for Instagram

You can use the app for a company or store’s IG accounts. Here are some samples based on a Mad Cakes Black Chocolate Indulgence photo. If you need ideas for your IG post, this tool can suggest copy that’s simple and straightforward for IG. Depending on your product or service, it suggests content that typically targets your customers base.

Video Writing Templates for YouTube

Next, offers specialized templates for videos, specifically for platforms such as YouTube. But I also think you can use the content similarly if you’re posting on other video sites. However, the suggestions are based on content with high traffic on YouTube. It includes the following features:

Video Topic Ideas: For brainstorming video content concepts that rank well on YouTube. For example, your initial topic is baking homemade cake. It’s a useful tool for letting you know what people are actually interested in. It gives you an idea what to work on right off the batt. Here are the AI’s suggestions. It mentions concepts for cake baking videos many people look for:

Video Script Outline: Helps make script outlines for any topic. However, this works more suitably for how-to and listicle type videos, not the ones with a narrative. The example below for how to spot aurora borealis or Northern lights. From the AI suggestions, you can choose the best strategies to come up with your own outline. I noticed many suggestions can be too general, besides the more specific ones I posted below. It’s still best to do your own research to make your video content more nuanced and unique. Otherwise, you may just parrot what other content creators have already done.

Video Titles: Like the other templates, there’s also a video title feature. As an example, many users on YouTube like to create content about shows or films. Suppose you want to write a feature about the anime Attack on Titan. For the suggestion, the AI actually came up with pretty awesome titles and topics you can start researching on. While this is based on high-traffic fan search, what you can do is watch what’s already there. This will help you come up with more unique insights about the show that has not been tackled. Again, try to focus on what would set your content apart from what’s already there.

Blog Post Templates provides templates that help you conceptual blog posts for your brands. It has tools to help you brainstorm topic ideas and outline your content. These suggestions are all based on high ranking topics on Google. It also comes with features that help compose blog post introductions and conclusions.

  • Blog Post Topic Ideas
  • Blog Post Outline
  • Blog Post Intro Paragraph
  • Blog Post Conclusion Paragraph

For the example, let’s focus on the topic template. I used the earlier example, Best Shape, which is an imaginary non-invasive weight loss service. See the AI’s suggestions below.

Jasper’s results show topics that trend around non-invasive weight loss methods. Trending topics around your market is always good to know. For ideas on blog topics, I think will really be a useful tool. If you need help structuring your outline, I think it’s worth using it especially if you’re having trouble with organization.

Personally, after getting different topics, you can start writing your post without the app. You won’t need it especially if you already have an idea what to write. It’s still better to do proper research than rely on the app to add information on your post. As you’ve noticed, it has a tendency to supply the incorrect information, which you must diligently edit.

Would I Recommend This Software?

After crash testing, I would recommend this tool to agencies or individuals that deal with extensive online copywriting and product rewrites. They will benefit the most by eliminating the time-consuming process of doing product descriptions. I would also recommend it for businesses that run social media campaigns, including Google and Amazon ads. This will help generate and organize copy ideas faster, especially if you have a lot of products and services to promote. And because the AI suggestions are based on high-ranking topics, you have a better idea of what your client base is also looking for. It can also enhance messaging concepts and help brainstorm new campaign ideas for a product or brand. Just remember to always edit the content suggestions.

On the other hand, I would not recommend this app for long-form writing. I do not think it is ideal for any writing that requires a lot of research. Because the AI suggestions tend towards incorrect information, you’re better off researching current data on your own. It’s an interesting tool for wring stories, but I also worry authors might be too reliant on the app for plot ideas. There is a difference between carefully worded prose versus long-winded sentences composed by this app. Human writing is still more precise with expression, which the AI has yet to learn.

While it’s a good tool to have, the bottom line is, you still need to edit your content. It will help you structure your outline and compose your post. However, the impetus for writing and the direction it will take is still on you, the writer. My verdict? AI writing technology won’t fully replace humans anytime soon.

Update: This article was updated in May of 2022 to reflect's AI writing bot name changed from Jarvis to Jasper. No other changes have been made since the original publication of this article.


On Wednesday SEMrush priced their IPO at $14 a share & listed Thursday.

There have been many marketing and online advertising companies which are publicly traded, but few that were so focused specifically on SEO while having a sizeable market cap. According to this SeekingAlpha post at the IPO price SEMrush had a valuation of about $1.95 to $1.99 billion. For comparison sake, here are some other companies & valuations.

  • Facebook acquired Instagram for $1 billion.
  • Google acquired YouTube for $1.65 billion.
  • Yelp trades at around a $2.9 billion market cap.
  • Yahoo! was acquired by Verizon for $4.48 billion.
  • Hubspot has a market cap of around $20.4 billion.

A couple years ago Gannett bought AdWords reseller WordStream. A few years before that they bought ReachLocal. The Hearst publishing empire also bought iCrossing long ago. Marin Software remains publicly traded, but they are only valued at about $20 million.

Newspapers reselling Google AdWords ads isn't really SEO though. Beyond those sorts of deals, many of the publicly traded SEO stuff has been only tangentially relevant to SEO, or crap.

There are some quality category-leading publishers which use SEO as a means of distribution but are not necessarily an SEO service provider like TripAdvisor, BankRate, and WebMD. Over time many of these sorts of companies have been gobbled up by Red Ventures or various private equity firms. Zillow, Yelp and TripAdvisor are some of the few examples which still exist as independent companies.

So that puts most of the publicly traded SEO stuff in one of the following categories...

  • small scale - does anyone other than Andy Beal & Mike Grehan still remember KeywordRanking / WebSourced / Think Interactive / MarketSmart Interactive?
  • hope and nope - sites like were repeatedly acquired but never really gained lasting relevance.
  • affiliate networks - which reliant on partners with SEO traffic like Quinstreet & Commission Junction. many affiliate networks were hit hard as the barrier to entry in SEO increased over the years. Quinstreet is doing well in some verticals but sold their education division to Education Dynamics for $20 million. CJ was part of the Publicis Groupe acquisition of Epsilon.
  • pump and dump scams - Demand Media, owner of eHow, which later rebranded as Leaf Group & still trades at a small fraction of their IPO price.

[Editorial note: 8 days after writing this post LEAF announced a $304.3 million all cash buyout offer from Graham Holdings at 21% above current market prices and was trading at $8.63 a share. If you bought shares at $40 or $30 or $20 and hoped it would at some point come back - nope - the losses are crystalized on a take out. Graham Holdings formerly owned the Washington Post but sold it to Jeff Bezos 8 years ago for $250 million.]

The one lasting counter-example to the above is Barry Diller's IAC. [edit: added ... here is the WSJ recommending the stock 3 months later, even after a big run]

IAC's innovation ecosystem is surreal. Across time & across markets Diller is the best creator of vertical leading properties later spun off as their own companies. He's owned Expedia, TripAdvisor, LendingTree, HomeAdvisor,, TicketMaster and so many other category leaders.

His buying of did not pan out as well as hoped as web browsers turned the address bar into a search box, his ability to differentiate the service went away after they shut down the engine in 2008, he was locked out of mobile search marketshare by default placement contracts & Google pushed back against extension bundling, but just about everything else he touched turned to gold.

A lot of IAC's current market cap is their ownership of Vimeo, which by itself is valued at $6 billion.

[Added a section on Vimeo here since it was spun out after this post was originally published.] Vimeo was a throw in when IAC bought CollegeHumor owner Connected Ventures. IAC was willing to sell Vimeo to Kodak for around $10 million over a decade ago, but there was no transaction. Around that time I ran a membership website here and we were going to use Vimeo for delivery of our videos but they deleted our paid subscription claiming Vimeo wasn't for businesses and was just for artistic uses. They probably did that hundreds or thousands of times over the years and then realized ... wait, we should allow businesses to use this, everyone else will just upload to YouTube. So they switched focus to business use, YouTube kept increasing ad load, and Vimeo kept becoming more appealing on a relative basis. This year YouTube updated their terms of service allowing them to monetize and and all uploaded videos, which only makes Vimeo look that much more appealing to businesses which are on the fence about paying a small monthly subscription for video hosting. When IAC spun out Vimeo this year (VMEO) it was valued at north of $6 billion. Someone like Microsoft could buy it and promote it in Bing search results the way Google does YouTube.

What is the most recent big bet for Barry Diller? MGM. Last August he bet $1 billion on the growth of online gambling. And he was willing to bet another billion to help them acquire Entain:

IAC has to date invested approximately US$1 billion in MGM with an initial investment thesis of accelerating MGM’s penetration of the $450 billion global gaming market. IAC notes in its letter of intent that IAC continues to strongly support this objective for MGM whether or not a transaction with Entain is consummated.

Barry Diller not only accurately projects future trends, but he also has the ability to rehab broken companies past their due dates.

The New York Times bought for $410 million in 2005 & did little with it as its relevance declined over time as its content got stale, Wikipedia grew and search engines kept putting more scraped content in the search results. The relentless growth of Wikipedia and Google launching "universal search" in 2007 diminished the value of even as web usage was exploding.

IAC bought from the New York Times for $300 million in August of 2012. They tried to grow it through improving usability, content depth and content quality but ultimately decided to blow it up.

They were bold enough to break it into vertical category branded sites. They've done amazingly well with it and in many cases they rank 2, 3, 4 times in the SERPs with different properties like TheSpruce, TheBalance, Investopedia, etc. As newspapers chains keep consolidating or going under, IAC is one of the few constant "always wins" online publishers.

At its peak TheBalance was getting roughly 2/3 the traffic generated.

Part of the decline in the chart there was perhaps a Panda hit, but the reason traffic never fully recovered is they broke some of these category sites into niche sites using sub-brands.

All the above search traffic estimate trend charts are from SEMrush. :)

I could do a blog post titled 1001 ways to use SEMrush if you would like me to, though I haven't yet as I already have affiliate ads for them here and don't want to come across as a shill by overpromoting a tool I love & use regularly.

I tend to sort of "not get" a lot of SaaS stocks in terms of prices and multiples, though they seem to go to infinity and beyond more often than not. I actually like SEMrush more than most though & think they'll do well for years to come. I get the sense with both them and Ahrefs that they were started by programmers who learned marketing rather than started by marketers who cobbled together offerings which they though would sell. If you ever have feedback on ways to improve SEMrush they are fast at integrating it, or at least were in the past whenever I had feedback.

When SEMrush released their S-1 Dan Barker did a quick analysis on Twitter.

Some stats from the S-1: $144 million in annual recurring revenues @ 50% compound annual growth rate, 76% gross margins, nearly 1,000 employees and over 67,000 paying customers.

At some point a lot of tool suits tend to overlap because much of their data either comes from scraping Google or crawling the open web. If something is strong enough of a point of differentiation to where it is widely talked about or marketed then competitors will try to clone it. Thus spending a bit extra on marketing to ensure you have the brand awareness to be the first tool people try is wise. Years ago when I ran a membership site here I paid to license the ability to syndicate some SEMrush data for our members & I have promoted them as an affiliate for what seems like a decade now.

When Dan Barker did his analysis of the S-1 it made me think SEMrush likely has brighter prospects than many would consider. A few of the reasons I could think of off the top of my head:

  • each day their archive of historical data is larger, especially when you consider they crawl many foreign markets which some other competitive research tools ignore
  • increasing ad prices promote SEO by making it relatively cheaper
  • keyword not provided on organic search means third party competitive analysis tools are valuable not only for measuring competitors but also measuring your own site
  • Google Ads has recently started broadening ad targeting further and hiding some keyword data so advertisers are paying for clicks where they are not even aware what the keyword was

That last point speaks to Google's dominance over the search ecosystem. But it is also so absurd that even people who ran AdWords training workshops point out the absurdity.

In Google maximizing their income some nuance is lost for the advertiser who must dig into N-Gram analysis or look at historical data to find patterns to adjust:

The account overall has a CPA in the $450 range. If the word ‘how’ is in the query, our CPA is over double. If someone searches for ‘quote,’ our CPA is under $300. If they ask a question about cost, the CPA is over $1000. Obviously, looking for quotes versus cost data is very different in the eyes of a user, but not in the matching search terms of Google.

Every ad network has incentive to overstate its contribution to awareness and conversions so that more ad budget is allocated to them.

  • Facebook kept having to restate their ad stats around video impressions, user reach, etc.
  • Facebook gave themselves a 28 day window for credit for some app installs.
  • Google AMP accidentally double counted unique users on Google Analytics (drives adoption = good).
  • Google Analytics came with last click attribution, which over-credits the search channel you use near the end of a conversion journey.

There are a lot of Google water carriers who suggest any and all of their actions are at worst benevolent, but when I hear about hiding keyword data I am reminded of the following quote from the Texas AG Google lawsuit.

"Google employees agreed that, in the future, they should not directly lie to publishers, but instead find ways to convince publishers to act against their interest and remove header bidding on their own."

That lawsuit details the great lengths Google went to in order to leverage their search monopoly to keep monopoly profit margins on their display ad serving business.

AMP was created with the explicit intent to kill header bidding as header bidding shifted power and profit margins to publishers. Some publishers saw a 50% rise in ad revenues from header bidding.

Remember how Google made companywide bonuses depend on the performance of the Google Facebook clone named Google+? Google later literally partnered with Facebook on a secret ad deal to prevent Facebook from launching a header bidding solution. The partnership agreement with Facebook explicitly mentioned antitrust repeatedly.

When a company partners with its biggest direct competitor on a bid rigging scheme you can count on it that the intent is to screw others.

So when you see Google talk about benevolence, remember that they promise to no longer lie in the future & only deceive others into working against themselves via other coercive measures.

We went from the observation that you can't copyright facts to promoting opinion instead:

to where after many thousands of journalists have been laid off now the "newspaper of record" is promoting ponzi scheme garbage as a performance art piece:

Is it any wonder people have lost trust in institutions?

The decline of was literally going to be terminal without the work of Barry Diller to revive it. That slide reflected how over time a greater share of searches never actually leave Google:

Of those 5.1T searches, 33.59% resulted in clicks on organic search results. 1.59% resulted in clicks on paid search results. The remaining 64.82% completed a search without a direct, follow-up click to another web property. Searches resulting in a click are much higher on desktop devices (50.75% organic CTR, 2.78% paid CTR). Zero-click searches are much higher on mobile devices (77.22%)

The data from the above study came from SimilarWeb, which is another online marketing competitive research tool planning on going public soon.

Google "debunked" Rand's take by focusing on absolute numbers instead of relative numbers. But if you keep buying default placements in a monopoly ecosystem where everyday more people have access to a computer in their pocket you would expect your marketshare and absolute numbers to increase even if the section of pie other publishers becomes a smaller slice of a bigger pie.

Google's take there is disingenuous at the core. It reminds me of the time when they put out a study claiming brand bidding was beneficial and that it was too complex and expensive for advertisers to set up a scientific study, without any mention of the fact the reason that would be complex and expensive is because Google chooses not to provide those features in their ad offering. That parallels the way they now decide to hide keyword data even from paying advertisers in much the same way they hide ad fees and lie to publishers to protect their ad income.

Google suggests they don't make money from news searches, but if they control most of the display ads technology stack & used search to ram AMP down publishers throats as a technological forced sunk cost while screwing third party ad networks and news publishers, Google can both be technically true in their statement and lying in spirit.

"Google employees agreed that, in the future, they should not directly lie to publishers, but instead find ways to convince publishers to act against their interest and remove header bidding on their own."

There are many more treats in store for publishers.

Google Chrome stopped sending full referrals for most web site visitors late last year. Google will stop supporting third party cookies in Chrome next year. They've even floated the idea of hiding user IP addresses from websites (good luck to those who need to prevent fraud!).

Google claims they also going to stop selling ads where targeting is based on tracking user data across websites:

"Google plans to stop selling ads based on individuals’ browsing across multiple websites, a change that could hasten upheaval in the digital advertising industry. The Alphabet Inc. company said Wednesday that it plans next year to stop using or investing in tracking technologies that uniquely identify web users as they move from site to site across the internet. ... Google had already announced last year that it would remove the most widely used such tracking technology, called third-party cookies, in 2022. But now the company is saying it won’t build alternative tracking technologies, or use those being developed by other entities, to replace third-party cookies for its own ad-buying tools. ... Google says its announcement on Wednesday doesn’t cover its ad tools and unique identifiers for mobile apps, just for websites."

Google stated they would make no replacement for the equivalent of the third party cookie tracking of individual users:

"we continue to get questions about whether Google will join others in the ad tech industry who plan to replace third-party cookies with alternative user-level identifiers. Today, we’re making explicit that once third-party cookies are phased out, we will not build alternate identifiers to track individuals as they browse across the web, nor will we use them in our products. We realize this means other providers may offer a level of user identity for ad tracking across the web that we will not — like PII graphs based on people’s email addresses. We don’t believe these solutions will meet rising consumer expectations for privacy, nor will they stand up to rapidly evolving regulatory restrictions, and therefore aren’t a sustainable long term investment."

On the above announcement, other ad networks tanked, with TheTradeDesk falling 20% in two days.

Competing ad networks wonder if Google will play by their own rules:

“One clarification I’d like to hear from them is whether or not it means there’ll be no login for DBM [a historic name for Google’s DSP], no login for YouTube and no login for Google properties. I’m looking for them to play by the same rules that they so generously foisted upon the rest of the industry,” Magnite CTO Tom Kershaw said.

Regulators are looking into antitrust implications:

"Google’s plan to block a popular web tracking tool called “cookies” is a source of concern for U.S. Justice Department investigators who have been asking advertising industry executives whether the move by the search giant will hobble its smaller rivals, people familiar with the situation said."

The web will continue to grow more complicated, but it isn't going to get any more transparent anytime soon.

"Google employees agreed that, in the future, they should not directly lie to publishers, but instead find ways to convince publishers to act against their interest and remove header bidding on their own."

As the Attention Merchants blur the ecosystem while shifting free clicks over to paid and charging higher ad rates on their owned and operated properties it increases the value of neutral third party measurement services.

The trend is not too hard to notice if you are remotely awake.

While I was writing this post Google announced the launch of a "best things" scraper website featuring their scraped re-representations of hot selling items. And they are cross-promoting competitors in "knowledge" panels to dilute brand values & force the brand ad buy.

Shortly after Google launched their thin affiliate scraper site full of product ads they announced an update to demote other product review sites.

Where Google can get away with it, they will rig things in their favor to rip off other players in the ecosystem:

Google for years operated a secret program that used data from past bids in the company’s digital advertising exchange to allegedly give its own ad-buying system an advantage over competitors, according to court documents filed in a Texas antitrust lawsuit. The program, known as “Project Bernanke,” wasn’t disclosed to publishers who sold ads through Google’s ad-buying systems.

If I could give you one key takeaway here, it would be this:

"Google employees agreed that, in the future, they should not directly lie to publishers, but instead find ways to convince publishers to act against their interest and remove header bidding on their own."

The Wrong People Won

Chasing New Markets

My initial attraction toward SEO and the web was largely that it was like a new and parallel world that bypassed many traditional gatekeepers.

I wrote an ebook which originally had inconsistent formatting and it was riddled with spelling and grammar errors. I learned to write by writing poorly and often while reading great writers daily.

Ultimately it did not matter that my efforts were subpar on some fronts as few people read early copies, and I was receptive to feedback on how to improve it and rapidly did.

The above process ... growing while few people see your ugly work ... is actually one of the advantages of *NOT* taking venture capital. You get to learn at your own pace while risks are low and only really lean into something when you know it is working. You keep making small bets that won't kill you and then when something works better than you expect you can *REALLY* lean into it.

I ultimately did that with SEO, blogging, and a couple other areas I can't mention too much as I had partners on some projects.

This blog never even started as its own site. It was a section on a different site that was spun out to become its own site when it was obvious blogs were being algorithmically over-promoted due to the cross linking from other bloggers and the instant exposure RSS feeds offered.

Instead of begging a book publisher to publish a book I had a higher margin product and the book publishers were begging me. The market was inverted and an outcast won by bypassing traditional gatekeepers.

When SEO was easy it was the same sort of deal. As long as you tried to learn about what the algorithms valued & put effort behind it you could rank for almost anything.

Early on that meant begging, buying, or borrowing links any way you could. If a project was throwing off big money you'd try public relations and to get high quality links to help reinforce the position and increase its longevity. But even junky links worked fantastic back in the day. That's part of why there was so much blog comment spam, referrer spam, expired domains, cheeseball web directories which actually had pagerank in the URL, article directories, private blog networks, all sorts of other paid links like, etc. etc. etc.

New channels provide new opportunities. Small players prove the model, drive adoption, and then over time the affiliate or independent publisher is replaced by some big publisher or a scrape-n-displace offering from the central market operators.

The Media Water Cycle

If you take a broad enough view of the world the above sort of water cycle repeatedly happens across all media formats and channels.

  • New channels emerge
  • Smaller players and hobbyists are attracted to the new and shiny object
  • Limited competition & regulation
  • Channel grows wildly
  • Channel locked down by regulation or a monopoly

When the channels are new they have the greatest chance of failure, but the biggest potential rewards for early adopters.

As channels are established and competition increases almost all the profit margins get handed over to the central market operator. Everything gets adjust on an "as needed" basis. Anything that hands too much of the profits over to a third party publisher gets cloned by the central network operator, becomes against the terms of service, or is algorithmically or manually neutralized by the central market operators.

  • affiliates used to be able to sit at the end of the conversion funnel and extract profits from the most valuable keywords, but new algorithmic signals make it hard to stay competitive with limited value add, differentiation, or brand building
  • commercial keywords are all ads in the search results above the fold & many brands feel the need to bid on their pre-existing brand equity for defensive purposes
  • Google hid keyword data from organic search & later started to hide some from paid search campaigns as well.
  • the Chrome browser by default only allows extensions to be downloaded from their official store & while Google got a lot of Chrome distribution through negative option bundling on Flash security updates, they prohibit app bundling in their app store
  • Apple's iOS and Google Android allow the central network operators to track third party app usage. The Apple Appstore and Google Play have mandatory 30% rakes and may disallow certain widely used apps after those features have been baked into the operating system or cloned and default bundled on new phones.
  • YouTube takes a 45% revenue share rake & the ad inventory is sold exclusively through Google tools where Google takes up to another 20% rake off the top
  • Amazon uses your sales data and product design to create what amounts to an effective clone job of it (going so far as to say there are fake safety issues to demand to see where it was manufactured) and then you are forced to bid on your own brand as Amazon gives itself free ads on your brand for their product clone job
  • Google and Facebook try to suck content into their networks via Instant Articles and AMP. Google gives AMP priority placement in their search results (just like they did previously with Google+, Google Checkout, Google Base / Google Shopping / YouTube / etc etc etc).
  • Rather than competing, Google and Facebook partnered to illegally bid rig auctions to destroy header bidding & preserve monopoly profit margins, keeping control over external publishers. Google also pushes "privacy" obfuscation which harms third party publishers and third party ad networks while bypassing those firewalls for its own ad network. They are also looking to use their web browser to do away with cookies, further kneecapping other ad networks.
  • Early Pinterest Ads sent users offsite and often cost only a couple cents a visit while all the internal cross promotion & viral spread across Pinterest was effectively free. Then over time advertisers start getting charged for pins even being opened and getting a user to actually leave Pinterest and click through can cost $5 or $10 a click. Long after I saw Reddit threads about how I was a washed up hack who could not compete in the modern market I literally used Pinterest to seed the growth of a site which now gets about a million organic search visits a month. I recently tried further promoting that site on Pinterest in some new areas, but the economics no longer works for that particular site on that channel.

Oligarchs Don't Stay in Power by Being Fair

If you play by the rules suggested by private market participants you are betting that they won't dramatically change their ecosystem at the drop of a hat and they won't compete against you.

And that bet is a REALLY bad bet.

Networks do not stay on top & in control by stagnating. They change with society & if they are influential enough they also change the structure of society.

The Texas AG lawsuit of Google for manipulating the online display ad market lays bare how power works:

Google employees agreed that, in the future, they should not directly lie to publishers, but instead find ways to convince publishers to act against their interest and remove header bidding on their own.

I could easily write a 100 page blog post on that lawsuit while feeling guilty for leaving many things out.

For example, did you know Google stole AdSense earnings from publishers in the AdTrader ad network and lied about refunding that money to advertisers as AdTrader also managed some of the advertiser accounts which got a $0.00 rebate:

We confirmed through multiple sources, both within and outside of Google, through our Google invoices, and data collected from Google APIs that Google never actually refunded any of the confiscated publisher earnings to the advertisers. In fact, Google’s own support team admitted that they never had a system in place for such refunds.

Google is the network I have studied most and know the most about, though others certainly know Facebook equally well. All the large networks growth the predacious exploits.

Even with limited Facebook usage I know they have at various points in time promoted: games, hype headline fake news, lists and viral quiz junk from Buzzfeed, real actual news sites, the Instant Articles version of real actual news, live video, friend content, etc. Facebook also bought Onavo, a VPN network to track the growth of competing apps. That data was used to inform their WhatsApp purchase. And they could see which features from what external networks they should clone, like when Instagram copied much of SnapChat's offering.

You can follow the Facebook terms of service in everything you do, but the odds of that delivering you real and sustainable profit streams is low.

"You can be unethical and still be legal that’s the way I live my life" - Mark Zuckerberg

Optimize and Reinvent

Few publishers will be experts at both optimizing for the flaw or overpromotion in the current algorithm or network set up AND being good at reinventing themselves to appeal to the algorithms of tomorrow. You ultimately want to use some of any excess profits to build a destination people seek out so you are less dependent on the central network operators.

At the same time, if you ignore the algorithms and just hope for the best you are probably going to lose to a competitor who clones most of your strategy AND manipulates the result set.

You sort of have to figure out what is being over-promoted today AND then try to figure out what will matter tomorrow, while reinvesting profits to the point you are no longer really faking it until you make it.

Realizing that all success is temporary is vital to encourage yourself to take advantage of the opportunities in front of you, while also ensuring you have a plan B in place that acts as a bridge to tomorrow in case your primary channel bombs.

Almost all profit margins (particularly for newer players lacking access to connections, massive cashflows, strong legacy brands, etc.) come from operating somewhere in the gray area. Behave in a manner that is legal, but push the boundaries of terms from other players.

Google funded eHow. Demand Media was ultimately a pump and dump operation. Those who followed it late got their asses handed to them, but those who got in early had plenty of profits they could reinvest in other lower risk ventures. At one point Mahalo publicly listed their page-level earnings data. One of my buddies went through and put that keyword list through TextBroker and uploaded a few hundred articles to an old blog. After about a year that led to a free house for one of their family members. :D

Now Google has far more data to use so it is hard to be anywhere near as exploitative or lowbrow as an eHow or a Mahalo was and expect that stuff to back out.

When Matt Cutts was on TWIG in 2013 he stated:

If you want to stop spam, the most straight forward way to do it is to deny people money because they care about the money and that should be their end goal. But if you really want to stop spam, it is a little bit mean, but what you want to do, is break their spirits. There are parts of Google algorithms specifically designed to frustrate spammers. Some of the things we do is give people a hint their site will drop and then a week or two later, their site actually does drop. So they get a little bit more frustrated. So hopefully, and we’ve seen this happen, people step away from the dark side and say, you know what, that was so much pain and anguish and frustration, let’s just stay on the high road from now on.
Some of the stuff I like best is when people say "you know what, this SEO stuff is too unpredictable, I am just going to write some apps."

This past year is the year when "writing some apps" was revealed to have the same core problems that SEO has. Central market operators grabbing their tithings (fight between Apple and entities like Spotify and Epic Games, Google Play pushing through similar 30% rake requirements) and then outright banning apps like Parler from their app stores.

COVID-19 Accelerated Shift to the Web

The COVID-19 pandemic moved everyone and everything online.

The ad money follows the attention stream. If the central network operators pay creators nothing then those creators who have a following will find other ways to monetize. Cygnus was early to SEO and he was early to influencer marketing.

Selling a sliver of attention and then using that funds flow to improve website usability, website design, content quality, brand awareness, reach, etc. ... is usually going to work out better for most people than trying to raise venture capital. Many small bets and incremental improvements yields much higher odds of success than a few really big bets.

Speaking of bets, I follow the stock market a bit because it teaches a lot about human psychology, markets and marketing.

Well before the COVID-19 crisis happened the repo market froze. In fact, the Federal Reserve was discussing alternative ways to fund the market's liquidity without looking like they were directly subsidizing and bailing out hedge funds:

the new approach could also create political problems for policy makers, analysts said. The problem centers on the central bank lending directly to hedge funds, the little-regulated investment vehicles that tend to serve wealthy or institutional investors. ... Though hedge funds are key participants in the market—where they both borrow and lend cash—lending to them directly through the FICC would raise questions about whether the government was backstopping their bets, analysts said.

When the COVID-19 crisis happened optics no longer mattered. Bailouts ensued. Without them levered hedge funds were screwed as many instruments became illiquid and spreads blew out even in bedrock stable markets:

Of particular concern: The hedge funds were using trading strategies similar to those employed by Long-Term Capital Management, a fund that collapsed in 1998 and nearly caused a financial meltdown. The bet that hedge funds were making earlier this year was simple enough. Called a basis trade, it involved exploiting a price difference in the Treasury market, generally by selling Treasury futures contracts — promises to deliver a bond or note at a set price on a set date — and buying the comparatively cheap underlying securities.

Shiny New Object to Bet On

Toward the end of last year and early this year Bitcoin was a rocket ship on the thesis of mass money printing leading to currency debasement and revaluing finite alternatives to fiat cash upward.

And then regulators began dropping hints while banks started to put the breaks on it. And XRP got kicked hard by the SEC, leading to delisting.

Tether may be an absolute scam (it's hard to short Patio11's knowledge), but in spite of that there are a lot of retail traders bored at home chasing anything that moves. There are ETFs like GBTC sucking up a huge share of the Bitcoin float with no intent of ever liquidating any of the position.

If sports and society shut down and people are stuck in their homes gambling is an unsurprising source of entertainment. Barstool Sports founder David Portnoy got this and quickly became a day trader when he didn't have any sports to talk about. :D

Above I mentioned a bit how the Federal Reserve was ultimately bailing out hedge funds. In an easy money market where central banks are printing tons of money what a lot of hedge funds do is buy higher beta growth names while shorting lower beta value stocks, particularly if they feel those companies are destined to go under.

In some cases the short bets believe ideas from a category apply to a specific company in a way they do not. And that can lead to a massive short squeeze, especially if the company announces a buyback and/or insiders buy.

In other cases, the shorts are so confident in their position, they go HOG WILD with low interest leverage and literally short the entire float of a company, trying to drive it into bankruptcy.

Recently Melvin Capital and some other well-connected hedge funds went short GameStop's stock and people who visited a Subreddit named WallStreetBets took the other side of that position.

Here is the original thread from 4 months ago discussing the gamma squeeze.

GME has a 52-week low of $2.57. After being pumped by the Subreddit the stock closed today at $347.51, leading to billions in losses for hedge funds which shorted over 100% of the stock.

The hedge funds that shorted over 100% of a stock ... were market manipulators aiming to manipulate a market. They were counterfeiting:

how do you get 130% of the available shares short? It would seem impossible and is unless someone cheats.

There are some players in the market who have "market maker" status but also trade their own books or have cross-interests with those who do. Allegedly there are "Chinese walls" between those pieces (or interconnected entities.) Quite obviously that is a load of crap because otherwise what you've seen would be impossible but it clearly not only has happened before but is still happening to this day. These entities are how you wind up with short sales where the locate and borrow hasn't happened first and the position remains open across time. This is supposed to be illegal but other than a few hand-slaps in the futures markets for physical commodities I'm not aware of any criminal prosecution for doing it.

And let's be clear here: This practice is counterfeiting.

When they win, that is capitalism.

When they lose, they get bailed out, contact regulators and have pressure applied to prevent THE WRONG PEOPLE from winning.

The SEC published a statement on market volatility, the Biden administration mentioned it was watching GameStop, Nasdaq's CEO suggested halting trading to allow hedge funds to steamroll Reddit users, the Discord group for WallStreetBets was shut down, and Reddit (at least temporarily) banned the WallStreetBets subreddit for hate speech.

That WallStreetBets was temporarily nuked will likely make the degenerate gamblers even more aggressive.

You can see a lot of moves coming if you understand internet culture.

But in many ways we are now where the outcomes will be pre-determined in order to ensure THE RIGHT PEOPLE win.

Politicians will determine outcomes after the fact.

The more THE WRONG PEOPLE win, the more intervention there will be to correct the natural order.

Risk is much higher than most perceive because outcomes matter more than process & some multi-generational politically-connected wealth is losing badly to THE WRONG PEOPLE.

An upstart online stock broker set trade commission prices to zero. Other brokers followed. And now that broker is telling stock buyers which tickers they are no longer allowed to buy.

When THE WRONG PEOPLE win we find our two sided markets become one way trades.

Can that be called a marketplace or even an attempt at a remotely honest market?


And it is even worse than it looked initially, as Robinhood not only prevented customers from buying $GME stock, but created a cascading wave of selling by placing "theft by conversion" forced sell orders at market on customer accounts.

When Robinhood placed "at market" sell orders for their clients - WITHOUT THEIR KNOWLEDGE OR PERMISSION - they literally *created* the interim market bottom.

That is fraudulent, criminal market manipulation.

Only losers actually eat creative destruction:

"just like 2008, trading was shut down to save the hides of erstwhile high priests of “creative destruction.” Also just like 2008, there are calls for the government to investigate the people deemed responsible for unapproved market losses. ... it was all well and good for investment banks and executives of phoney-baloney companies to gorge themselves on funhouse profits on a funhouse economy, but when amateurs decided to funnel just a bit of this clown show into their own pockets, finance pros wailed like the grave of Adam Smith had been danced upon."

We are now at the point that the internet is no longer a spot for weirdo outcasts & instead it is reshaping the rest of society.

The times and methods change, but the players remain the same.

Thanks for your attention and your money:

Both of these stories are narratives for our very own Hunger Games, a spectacle that chews up the participants in the arena while delivering enormous profits to the networks (media, financial and political) that put them on. Media networks count their profits in eyeballs, in the attention the Games garner. Financial networks count their profits the old-fashioned way, in the sheer volume of dollar-generating order flow the Games produce. As for politicians, they get their most valuable coin of the modern realm – an issue. The wackos on the left get to propose insane transaction taxes. The wackos on the right get to tell us how much liBeRtY we are enjoying by giving Ken Griffin all of our money. The very serious centrists get to tell us about how we need “a national conversation” about the T+2 settlement issues raised here.

In Need of False Gods

After people get repeatedly screwed spite and revenge become motivators. Some will not mind napalming themselves so long as the entire ship goes down.

Part of a person as awful as Trump getting elected as president was micro-targeted South Park inspired videos sent to minorities reminding them of Hillary Clinton's super predators speech.

And who could forget her laughing about having the head of Libya murdered, a former nation which fell apart to such an extreme degree they had open air slave auctions.

Rescuing the Criminals, Dumping the Costs on You

Another part of Trump getting elected was Obama promising "Hope and Change" but then standing between banks and pitchforks for the intentional and malicious fraud that led to the 2008 economic blowup.

A Citigroup insider had the Obama cabinet picked out before he was even elected.

Citigroup was the biggest TARP recipient.

Citicorp is the same company which illegally merged with Travelers, then had that merger made legal after the fact by getting the Great Depression era Glass-Steagall Act regulation repealed:

''I think we will look back in 10 years' time and say we should not have done this but we did because we forgot the lessons of the past, and that that which is true in the 1930's is true in 2010,'' said Senator Byron L. Dorgan, Democrat of North Dakota. ''I wasn't around during the 1930's or the debate over Glass-Steagall. But I was here in the early 1980's when it was decided to allow the expansion of savings and loans. We have now decided in the name of modernization to forget the lessons of the past, of safety and of soundness.''

After the internet stock bubble popped the Federal Reserve lowered rates dramatically and left them there far too long, creating a massive hunt for yield. This led to a housing bubble and deteriorating loan standards with fog-a-mirror NINJA loans and similar dominating the market due to the insatiable demand for "risk free" yield. Entities like Citigroup created a ton of bogus mortgage paper they knew was garbage. Their entire board of advisors was repeatedly emailed by Richard M. Bowden about the fraud:

I started issuing warnings in June of 2006 and attempted to get management to address these critical risk issues. These warnings continued through 2007 and went to all levels of the Consumer Lending Group. We continued to purchase and sell to investors even larger volumes of mortgages through 2007. And defective mortgages increased during 2007 to over 80% of production.

If you control the government economic outcomes are determined by politics.

Citigroup was so confident in their control of the political outcomes they continued to dump bad loans on the FHA after Fannie Mae and Freddie Mac were forced into receivership.


"Squeezing the oligarchs, though, is seldom the strategy of choice among emerging-market governments. Quite the contrary: at the outset of the crisis, the oligarchs are usually among the first to get extra help from the government, such as preferential access to foreign currency, or maybe a nice tax break, or—here’s a classic Kremlin bailout technique—the assumption of private debt obligations by the government. Under duress, generosity toward old friends takes many innovative forms. Meanwhile, needing to squeeze someone, most emerging-market governments look first to ordinary working folk—at least until the riots grow too large. Eventually, as the oligarchs in Putin’s Russia now realize, some within the elite have to lose out before recovery can begin. It’s a game of musical chairs: there just aren’t enough currency reserves to take care of everyone, and the government cannot afford to take over private-sector debt completely.
From long years of experience, the IMF staff knows its program will succeed—stabilizing the economy and enabling growth—only if at least some of the powerful oligarchs who did so much to create the underlying problems take a hit.
But there’s a deeper and more disturbing similarity: elite business interests—financiers, in the case of the U.S.—played a central role in creating the crisis, making ever-larger gambles, with the implicit backing of the government, until the inevitable collapse. More alarming, they are now using their influence to prevent precisely the sorts of reforms that are needed, and fast, to pull the economy out of its nosedive. The government seems helpless, or unwilling, to act against them.
The third Citigroup bailout, in late February, converted government-owned preferred stock to common stock at a price significantly higher than the market price—a subsidy that probably even most Wall Street Journal readers would miss on first reading." - Simon Johnson, The Quiet Coup

Any government which intentionally subsidizes and promotes massive fraud undermines its legitimacy.

Citigroup winning while most people lost was *explicit* government policy:

“When you look at who benefits from the Chinese trade surplus and the US trade deficit, it’s the same group of people,” he said. In the US it was the banking elites, while in China it tended to be the political elites, but in both countries ordinary workers lost out

Obama was so rotten he made Trump look like a reasonable choice.

Soulless Corporations Promoting Racism as a PR Diversion

Who were the people hurt worst by Citigroup's fraud?

Poor minorities.

So it should come as no surprise Citigroup published "research" on how racism is holding back the U.S. economy.

Don't blame Citigroup for stealing your house, crashing the economy, and causing millions of people to lose their jobs. Instead, blame white people. Perhaps you could hit an old white man walking down the street in the back of the head with a brick and upload your crime videos to your social media channels. #hope #change

Large & corrupt companies which plunder society pretend to care about subgroups as a cheap form of public relations and to keep their brand from being associated with what they actually do.

Crash the economy, spread misinformation, then as people point fingers back and forth for your bad deeds everyone can blame the victims.

"Not only were many of those people who’d been foreclosed upon or laid off or forced to watch their 401Ks lose half their value still in emotional shock, but the underlying corruption was not exactly easy for them to see. Propaganda blasted out on every channel, to the effect that it was your own fault if you took on an adjustable-rate mortgage that went sideways, or bought too big of a house. People above all feel shame when they can’t pay their debts, and many took it to heart when pundits said the crash was caused by people buying houses they couldn’t afford.

Those criticisms often came out as racial politics, as conservative media figures hammered the theme of the “water drinkers” who crashed the economy at the expense of the “water carriers.” Listening to these takes, resentment in some neighborhoods grew toward the family down the street who’d been foreclosed upon, leaving a boarded-up eyesore on the block and collapsing property values for those left. The Tea Party movement, launched by a rant on CNBC against a proposed bailout for minority homeowners in particular, steered public anger away from Wall Street and toward the “bad behavior” of the “losers” down the street.
Why they were pissed off gets to the second question, about the bailouts, ZIRP, the TARP, even the CARES Act. While so many people went into personal tailspins from 2008 on, their nightmares were often compounded watching as the very people who caused the crash — including the banks and mortgage originators who knowingly pumped mountains of fraudulent subprime instruments into the economy — not only got saved but were further enriched, by bailouts and an array of extravagant Fed programs.

Some people got ripped off three times. First, they were personally sold dodgy exotic mortgages. Next, their retirement funds were sold the same kinds of dicey loans in the form of securities. Lastly, when it all blew up, they paid taxes to bail out the whole shooting match." - Matt Taibbi

No bank wants to have the brand Wells Fargo has earned for opening up millions of fake customer accounts to charge fees to, stealing people's cars after charging them for bogus force placed insurance policies, etc.

Executives at those companies concerned primarily with stock option values know being corrupt and donating to BLM is more profitable than running a business honestly & ethically. Fraud is alpha.

If Obama the president matched Obama the candidate the Citigroup board would have been imprisoned, that bank would have been dismantled, and the above "research" about racism which diverts attention away from crimes by the likes of Citigroup would not have been published.

Large institutions - particularly those which are bailed out after committing massive fraud - are able to survive market cycles. Most individuals carry debt of some sort (education, healthcare, housing, auto, other financed purchases). When the economy craters if they lose their job they may also lose their homes and be forced to sell whatever other financial assets they have near the market bottom to afford food.

Institutions vs Individuals

The pain of Citigroup's fraud was felt widely across the economy.

"I was in my early teens during the '08 crisis. I vividly remember the enormous repercussions that the reckless actions by those on Wall Street had in my personal life, and the lives of those close to me. I was fortunate - my parents were prudent and a little paranoid, and they had some food storage saved up. When that crisis hit our family, we were able to keep our little house, but we lived off of pancake mix, and powdered milk, and beans and rice for a year. Ever since then, my parents have kept a food storage, and they keep it updated and fresh. Those close to me, my friends and extended family, were not nearly as fortunate." - ssauronn

Citigroup's fraud led to many deaths of despair:

US life expectancy was rising almost every year for decades straight. However, it peaked in 2014, and has been in a multi-year sideways trend for the first time in decades. This recent flat-lining in life expectancy has been a uniquely US phenomenon. Life expectancy continues to increase in virtually every other highly-developed country/continent. Life expectancy went up from 2014-present in Japan, the Euro Area, Canada, Australia, etc.

Income & wealth inequality - particularly if it is driven from the combination of the offshoring of the industrial base Clinton & Bush did then the sort of fraud Citigroup did - often leads to a breakdown of cooperation across society, and then, arbitrary violence.

If you make people's lives miserable and tell them they are victims many of them will believe you.

Some of them will live down to the standards you set and see any isolated incident as a pattern of conduct which deserves retribution.

The media tells people economics is violence, words are violence, they are victims, they are owed something, and ... surprise ... that drives violence.

Violence is a (temporary) shortcut to status for young men with lots of testosterone but limited prospects or success in society.

Growing up in a single parent home on welfare only adds further fuel to that fire because there is not only a sense of entitlement and unfairness, but often elevated stress levels and a deep sense of shame and resentment.

My Daughter Was Nearly Killed by Racism

I now have a 4 year old daughter. I have screwed up a great many things in life, but I don't know anybody more confident than she is.

When my wife was pregnant with our only kid I nearly died from a sepsis infection & my daughter was nearly a miscarriage.

The above is not hyperbole.

Here I was in the hospital getting multiple IV antibiotics.

When they told me I might die soon I was like "oh well, that's that."

Then my wife came over and heard that & was crying uncontrollably. I then realized the sort of cascading set of dire outcomes and played it off like the infection was nothing while pushing to do whatever I could to get better fast before other bad outcomes happened.

A couple months later our dog died and my wife then gave an emergency early birth. His death caused an early term birth. If I had died a few months earlier then almost certainly my daughter would have been a miscarriage, then my wife likely would have committed suicide.

About a decade prior - around the time Obama was making Citigroup whole on their frauds while passing the costs onto the rest of society - a racist black guy sucker punched me while calling me nigger. That chipped the root of one of my teeth. Slowly over the next decade part of my jaw rotted away from an infection that exploded into near death in the middle of my wife's pregnancy. And my daughter nearly had no life.

Writing the above will have many people suggest it is I that am racist for suggesting the racist person who tried to kill me should have had a longer prison sentence for his other previous violent crime convictions, or maybe we should restructure the economy away from financial bubbles, monopolies, and offshoring.

I'm of the view that anyone who is convicted of multiple separate violent crimes should be permanently caged or put to sleep, because when you commit violent acts repeatedly you do not deserve to live as you are not only harming the person you sucker punch or such, but you could also end the life of their unborn child.

The sepsis happened while we were traveling. The initial hotel we were staying at was sold out on the final day so I just happened to stay in a hotel across the street from a hospital. A few hours before jumping on a 15 hour flight I went over to the hospital and they turned me away saying it was just a dental issue. Then my wife brought be back over, they looked at me, and were like ... oh, you are about to die.

That infection came back no less than 3 times. I had to get multiple teeth ripped out. I've had multiple fixed bridges.

If you add up the health expenses, emotional issues (more for my wife than me - much harder to lose someone you love than it is to die), inability to work, having teeth being wired in place, what seems to be dozens of dental visits, getting teeth ripped out repeatedly, etc ... my social "safety" net payment funding kids being born into broken homes with no dad not only nearly liquidated my family, but also cost millions extra.

I absolutely despise race baiters who promote arbitrary violence and the big crimebanks like Citigroup which plunder society leaving people hopeless.

Fuck those people with a rusty chainsaw.

Likewise the Marxist scum that founded Black Lives Matters and is buying about a house a year while promoting people like me being sucker punched by racist low-IQ pay-to-breed garbage or enslaved to pay for the "Marxist's" 3rd, 4th, or 5th estate.

I live on the other side of the world and thus do not get to vote on how 30%, 40%, or (if Biden uncaps FICA) 50%+ of my labor is spent.

Why do we need to remove the FICA cap?

So we can pay fraud-based prices for medicines used by others.

Last year when I ACHed income tax payments I sent in over 1,000 times what the president did.

One of my friends told me they didn't blame Trump they blamed the system, but I thought that was an absurd claim as a leader should not only comply with and improve rules, but they should also set an example.

The idea I should pay a thousand times more while having no vote or voice *AFTER* leaving on account of being nearly killed by a racist person who called me nigger, WHILE also being lectured about racism ... is a bit much.

The reasons I liked Trump (before the $750 income tax payments and nutbag January 6th fiasco) were:

  • he was hated by the media, so they'd cover wrongdoings (even making some up)
  • until the COVID-19 crisis hit, he was broadening the economy (which is why he got higher minority votes than any republican presidential candidate in decades in spite of the COVID-19 lockdowns)
  • his administration pushed through an antitrust lawsuit against Google for their monopolistic bundling practices (which will at least restrain Google slightly, provided Biden is not a third Obama term)

The above being said, the January 6th fiasco was absolutely idiotic, and looked like it was something out of South Park.

Obama's Third Term

Google's Eric Schmidt played a vital role in the Obama elections & administration. Their relationship was so close it was called "The Android Administration."

When the FTC investigated Google the Obama administration intervened to prevent justice. To pay back Eric Schmidt for his help on the presidential campaigns Obama's interventions undermined market competition for a decade:

Federal investigators were convinced: Google’s push to take over mobile internet searches was illegal. They had the evidence and urged their bosses to sue. But those politically appointed bosses overruled them. Nearly a decade later, the Justice Department and state regulators are suing Google over the same multibillion-dollar smartphone contracts that investigators for the Federal Trade Commission flagged years ago — and arguing that the deals present some of the strongest evidence that Google has built a monopoly.

The FTC had all the evidence they needed to prosecute along with absolute proof of intent to monopolize the market through illegal tying & bundling.

The FTC lawyers recommended suing.

But then the Obama administration full of future tech monopoly lobbyists stepped in and disappeared the case without action. They ignored the attorneys and used the staff economist claims rather than the work of the attorneys to justify disappearing the case based on limited search marketshare for mobile at the time.

About a decade ago Andy Rubin described Google's payments then to mobile carriers as "humungous." Those have only grown larger with time. What was once a small mobile search market is now the majority of search volume. Google now pays Apple at least $12 billion per year to retain default search placement across Apple devices.

Now Schmidt's shadowy "use AI everywhere in weaponry" startup is deeply embedded in the Biden administration. A Google lawyer is being considered for the top justice department inside the Biden administration, which would ensure ongoing INjustice is served.

We are back to an administration loved by the media. The controversy are hence reduced to casual magazine cover shoots.

Mainstream media: please serve your vital roll in society. Cover that casual photoshoot and not the Darth Vader aspects of Eric Schmidt, expansions of kill lists for suspects, etc.

The mainstream media & tech companies are so proud of election interference they literally brag about it. The following quote sounds like something out of Fox News or the New York Post, but it was published by Time:

the participants want the secret history of the 2020 election told, even though it sounds like a paranoid fever dream–a well-funded cabal of powerful people, ranging across industries and ideologies, working together behind the scenes to influence perceptions, change rules and laws, steer media coverage and control the flow of information. They were not rigging the election; they were fortifying it.

A half-year of violent demonstrations. Unelected private actors changing election laws & interpretations of election laws & illegally bundling private funds to change the outcome of an election. There were even Facebook pages dedicated to paying people to vote. And hundreds of thousands of people nationwide on standby to hold demonstrations just in case the vote does not go as they planned. It's a reach to call that democracy.

There still is some actual journalism being done though. I am glad to see articles like this one, which shows just how absurd this page is.

How many media outlets are telling you that we should nuke the Keystone pipeline for the environment, but then get the oil from half-way around the world from a murderous thug autocrat, who we give a free pass to for LITERAL MURDER because he has oil?

the White House is concealing the names of the seventy-six Saudi operatives to whom they are applying visa bans for participating in Khashoggi’s assassination, absurdly citing “privacy” concerns — as though those who savagely murder and dismember a journalist are entitled to have their identities hidden. ... The U.S. has instituted policies of torture, kidnapping, mass warrantless surveillance, and due-process-free floating prisons in the middle of the ocean where people remain in a cage for almost 20 years despite having never been charged with a crime. The Biden Justice Department is currently trying to imprison Julian Assange for life for the crime of publishing documents that revealed grave crimes by the U.S. government and its allies, and is attempting to do the same to Edward Snowden. One need not look toward the barbarism of U.S. allies to see what propagandistic dreck is the claim that the U.S. stands steadfastly opposed to authoritarianism in the world: just look at the U.S. Government itself.

A lot of the instability in society is not some accidental biproduct of something else, but is rather intentional government policy.

When rule of law only applies to some of the people some of the time instability can be arbitraged in both directions by those with access to capital and political power. Each additional slice of instability is another opportunity to go long or short some sector of the market.

What do you think has happened to the price of oil recently?

Up, up, up.

The same New York Times which published the above Biden headlines, gave Trump the following coverage:

“In Extraordinary Statement, Trump Stands With Saudis Despite Khashoggi Killing.” was the Times headline, in a piece that said Trump’s decision was “a stark distillation of the Trump worldview: remorselessly transactional, heedless of the facts, determined to put America’s interests first, and founded on a theory of moral equivalence.” The paper noted, “Even Mr. Trump’s staunchest allies on Capitol Hill expressed revulsion.”

What is important is WHO, not WHAT.

Literal murder doesn't actually matter, unless it can be used to aid in the character smear of someone you dislike.


"Free" Trade & Deindustrialization

Biden pushed against the "racist" attribution of the COVID-19 crisis to its source in China, though few have considered how "free trade" with a country with over a million slaves would impact living standards as it deindustrializes the country and destroys the middle class.

If a country has a live organ harvesting program for its own citizens, do we want to have close ties to it?

If a state-controlled economy dumps fentanyl into your country and repeatedly hacks thousands of companies for economic espionage & theft of trade secrets they deserve nothing but ire and disrespect, at least until those problems go away.

"Normalizing" relationships with such a country is idiotic. The only way to normalize those relationships is to undermine & crash their political & economic structure - reciprocate what they have done to you. Put the screws to them as they try to do to you, rather than letting them set up parallel systems to undermine you and sew internal division. Brutish authoritarians only understand force.

While we are seeking out a just global society, does LeBron James say "technically the Chinese Uighur slaves who make my Nike shoes are not black, so it is all good! #BLM"

A decade ago, no one would’ve put NBA superstar LeBron James and Apple CEO Tim Cook in the same family album, but here they are now, linked by their fantastic wealth owing to cheap Chinese manufacturing (Nike sneakers, iPhones, etc.) and a growing Chinese consumer market. The NBA’s $1.5 billion contract with digital service provider Tencent made the Chinese firm the league’s biggest partner outside America. In gratitude, these two-way ambassadors shared the wisdom of the Chinese Communist Party with their ignorant countrymen. After an an NBA executive tweeted in defense of Hong Kong dissidents, social justice activist King LeBron told Americans to watch their tongues. “Even though yes, we do have freedom of speech,” said James, “it can be a lot of negative that comes with it.” - Tablet

Free capital flows plus structural trade deficits from "free trade" with slave states = declining domestic living standards.

If you want lives to matter & have good outcomes you need to address the core issues. You want strong families, a growing middle class, and to lift trade partner countries up rather than having much of your citizenry see their living standards reduced to being near that of your worst trade partners.

If you have an average to below average IQ, did not come from wealth, have high living costs, and you must compete against literal slaves your life is probably going to suck.

Declining living standards can be masked temporarily through manipulating economic data, but fake data can't restore hopes and dreams and aspiration for something better.

That loss of hope will fuel deaths of despair, desperation, and a desire to believe in just about anything.

The race baiting "equality of outcomes" promoters only throw further fuel on the fire by telling people they are victims and pointing their ire in the wrong direction.

Burning down the local nail salon in a riot is not going to change the Federal Reserve bailing out hedge funds who are manipulating the stock market. It will not make the local economy more vibrant. It will not bring jobs back. It will not fix the free trade with slave state issue.

Instead of acting like an enraged victim, read Kurt Vonnegut's Harrison Bergeron and then consider what skills you can lean into to make a positive change in the world.

The process and outcome of that "free trade" with slave states & papering it over with increasing debt leverage was well known in advance: deindustrialization, consolidation, economic bubbles, lower living standards, more corrupt politics, mass migration waves, etc.

Look no further than this 1994 Charlie Rose video interview of Sir James Goldsmith.

Ultra-wealthy plutocrats were willing to partner with the CCP and sacrifice the US middle class in order to gain more wealth and political power.


Why did they trade with an authoritarian regime and send millions of American manufacturing jobs off to China thereby impoverish working Americans? Because it made them rich. They salved their consciences by telling themselves they had no choice but to deal with China: It was big, productive, and efficient and its rise was inevitable. And besides, the American workers hurt by the deal deserved to be punished—who could defend a class of reactionary and racist ideological naysayers standing in the way of what was best for progress?

But if Donald Trump saw decoupling the United States from China as a way to dismantle the oligarchy that hated him and sent American jobs abroad, he couldn’t follow through on the vision. After correctly identifying the sources of corruption in our elite, the reasons for the impoverishment of the middle classes, and the threats foreign and domestic to our peace, he failed to staff and prepare to win the war he asked Americans to elect him to fight.

And because it was true that China was the source of the China Class’ power, the novel coronavirus coming out of Wuhan became the platform for its coup de grace. So Americans became prey to an anti-democratic elite that used the coronavirus to demoralize them; lay waste to small businesses; leave them vulnerable to rioters who are free to steal, burn, and kill; keep their children from school and the dying from the last embrace of their loved ones; and desecrate American history, culture, and society; and defame the country as systemically racist in order to furnish the predicate for why ordinary Americans in fact deserved the hell that the elite’s private and public sector proxies had already prepared for them.

Alternatively put: "There’s class warfare, all right, but it’s my class, the rich class, that’s making war, and we’re winning." ― Warren Buffett

Become an Insider, or Get Used to Losing

For some people the web was a life raft, but a lot of the easy wins have already been had.

And the central network operators are getting more aggressive with scratch-your-back censorship for those in political power.

Sometimes it can be helpful to view the losses as personally targeted if that creates a fire that drives you to do something great

but that fuel burns fast...then what?

The only solution to the good ole boys club is to get big enough that you are no longer an outsider.

The hot shiny object has a lot of headlines, a lot of competition, and a lot of manipulation.

It is better to do something which is getting less attention but has more staying power.

As more and more services happen online, more and more of business profit margins are flowing online, and the online networks are having a massive impact on the portions of the economy which remain offline.

The central network operators can choose to ban an outgoing president while ignoring politicians who call for genocide in other markets to curry favor to political leaders.

As Zuck would say ...

"You can be unethical and still be legal that’s the way I live my life"

A central problem with the web is network effects and the winner-take-all structure of many markets. It creates a few gigantic winners, but many players along the remaining parts of the value chain get squeezed. You could say that getting hit hard by a Panda or Penguin algorithm update and having a business die overnight is a better outcome than the constant slow squeeze where things get just a little bit worse each month.

Monopolies lower wages. limit opportunities and retard innovation. Most the profits go to key players and shareholders while many jobs get shifted into semi-formal rolls.

You can work for Google and they promise that when you put in your letter at your other job to be one of their temp workers they won't change their mind and fire thousands overnight.


You can work in an Amazon warehouse until you physically break down and they might be so kind as to park an ambulance outside for you instead of wasting profit margin on air conditioning.

Even many of the creative works which are ultimately shunned by companies accustomed to risk-free monopoly profit margins will get squeezed as the work from home / remote work movement will create the next wave of offshoring jobs which people thought you couldn't really outsource.

If you live in a high cost area you had better do something you love so it is highly differentiated.

The only hope for players along the rest of the value chain is a shift away from the ad-dominated web to one where people pay for the services they like and the distribution outcome moves away from a star-based system to more of a bell curve.

The good news is many websites are removing friction and making it easier to test paid media options. Twitter recently acquired and integrated a paid newsletter service. But at the end of the day most people will eventually need to shift away from app stores and other controlled platforms so they can better differentiate their offering and have a sustainable business as platforms shift business models and what they prioritize to keep up with new trends.

The Attention Merchants dominating the web do not want to be low margin payment processors though, so they aren't going to make it easy to build a different web architecture where they become less influential.

Governments the world over are working with the large attention merchants & journalists to promote censorship & distort reality.

Google being based out of Bermuda for many years and growing like a weed during the recent recession while the offline economy cratered will lead to some new complicated global taxes which Janet Yellen has already gave a nod to. Politicians like Senator Elizabeth Warren are suggesting new wealth taxes and a 40% exit tax. If those get approved then the bars on where they kick in will fall after they are in place while the ultra rich find new ways to circumvent the law's intent (e.g. buy hard-to-value illiquid assets or create a self-managed charity that buys up tons of land & then change its status after that law goes away or some loophole is found in it).

Then there is the whole "Great Reset" where if lockdowns didn't kill off your business perhaps some other new regulations will (e.g. maybe carbon taxes to you to subsidize your competitor built off a coal power plant in China).

Tim Berners-Lee will likely end up saving the web he created by promoting decentralization.

If that doesn't work, we are stuck with Zuck and Eric Schmidt & their partners restructuring society as they see fit.

That would would be increasingly unjust, corrupt and violent.

So I am *REALLY* rooting for Tim Berners-Lee to pull a second rabbit out of a hat.

Apple Search

Google, Google, Google

For well over a decade Google has dominated search to where most stories in the search sphere were about Google or something on the periphery.

In 2019 Google generated $134.81 billion in ad revenues.

When Verizon bought core Yahoo three years ago the final purchase price was $4.48 billion. That amount was to own their finance vertical, news vertical, web portal, homepage, email & web search. It also included a variety of other services like Tumblr.

Part of what keeps Google so dominant in search is their brand awareness. That is also augmented by distribution as defaults in Chrome and Android. Then when it comes to buying search distribution from other players like Mozilla Firefox, Opera or Apple's Safari they can outbid everyone else as they are much better at monetizing tier 2 markets and emerging markets than other search companies are since they have such strong ad depth. Even if Bing gave a 100% revshare to Apple they still could not compete with Google in most markets in terms of search monetization.

Apple as a Huge Search Traffic Driver

In 2019 Google paid just under £1.2 billion in default payments for UK search traffic. Most of that went to Apple. Historically when Google broke out their search revenues by region typically the US was around 45% to 46% of search ad revenue & the UK was around 11% to 12%, so it is likely Google is spending north of $10 billion a year to be the default search provider on Apple devices:

Apple submitted that search engines do not pay Apple for the right to be set as the primary default search engine on its devices. However, our assessment is that Google does pay to be the primary default on Apple devices. The agreement between Google and Apple states that Google will be the default web search provider and the same agreement states that Google will pay Apple a specified share of search advertising revenues. We also note that Google does not pay compensation to any partners that set Google Search as a secondary option. This further suggests that Google’s payment to Apple is in return for Apple setting Google as the primary default.

Apple is glad to cash those checks & let Google handle the core algorithmic search function in the web browser, but Apple also auto-completes many searches from within the address bar via various features like website history, top hit, news, Siri suggested website, suggested sites, etc.

A Unique Voice in Search

The nice thing about Apple powering some of those search auto-complete results themselves is their results are not simply a re-hash of the Google search results so they can add a unique voice to the search marketplace where if your site isn't doing as well in Google it could still be promoted by Apple based on other factors.

High-traffic Shortcuts

Apple users generally have plenty of disposable personal income and a tendency to dispose of much of it, so if you are an Android user it is probably worth having an Apple device to see what they are recommending for core terms in your client's markets. If you want to see recommendations for a particular country you may need to have a specialized router targeted to that country or use a web proxy or VPN.

Most users likely conduct full search queries and click through to listings from the Google search result page, but over time the search autocomplete feature that recommends previously viewed websites and other sites likely picks up incremental share of voice.

A friend of mine from the UK runs a local site and the following shows how the Apple ecosystem drove nearly 2/3 of his website traffic.

His website is only a couple years old, so it doesn't get a ton of traffic from other sources yet. As of now his site does not have great Google rankings, but even if it did the boost by the Apple recommendations still provides a tailwind of free distribution and awareness (for however long it lasts).

For topics covered in news or repeat navigational searches Apple likely sends a lot of direct visits via their URL auto-completion features, but they do not use the feature broadly into the tail of search across other verticals, so it is a limited set of searches that ultimately benefit from the shortcuts.

Apple Search Ranking Factors

Apple recently updated their search page offering information about Applebot:

Apple Search may take the following into account when ranking web search results:

  • Aggregated user engagement with search results
  • Relevancy and matching of search terms to webpage topics and content
  • Number and quality of links from other pages on the web
  • User location based signals (approximate data)
  • Webpage design characteristics

Search results may use the above factors with no (pre-determined) importance of ranking. Users of Search are subject to the privacy policy in Siri Suggestions, Search & Privacy.

I have seen some country-code TLDs do well in their local markets in spite of not necessarily being associated with large brands. Sites which do not rank well in Google can still end up in the mix provided the user experience is clean, the site is useful and it is easy for Apple to associate the site with a related keyword.

Panda-like Quality Updates

Markets like news change every day as the news changes, but I think Apple also does some Panda-like updates roughly quarterly where they do a broad refresh of what they recommend generally. As part of those updates sites which were once recommended can end up seeing the recommendation go away (especially if user experience declined since the initial recommendation via an ad heavy layout or similar) while other sites that have good engagement metrics get recommended on related searches.

A friend had a website they sort of forgot that was recommended by Apple. That site saw a big jump on July 9, 2018 then it slid back in early August that year, likely after the testing data showed it wasn't as good as some other site Apple recommended. They noticed the spike in traffic & improved the site a bit. In early October it was widely recommended once again. That lasted until May of 2019 when it fell off a cliff once more. They had monetized the site with a somewhat spammy ad network & the recommendation mostly went away.

The recommendations happen as the person types and they may be different for searches where there is a space between keywords and the word is ran together. It is also worth noting Apple will typically recommend the www. version of a site over the m. version of a site for sites that offer both, so it makes sense to ensure if you used separate URLs that the www version also uses a responsive website design.

Indirect Impact on Google

While the Apple search shortcuts bypass Google search & thus do not create direct user signals to impact Google search, people who own an iPhone then search on a Windows computer at work or a Windows laptop at home might remember the site they liked from their iPhone and search for it once more, giving the site some awareness that could indirectly bleed over into impacting Google's search rankings.

Apple could also eventually roll out their own fully featured search engine.