My next book is The Reverse Centaur's Guide to Life After AI, out next month. Pre-order it now, including as a DRM-free audiobook or ebook, at my Kickstarter, and help me continue to prove that DRM-free isn't just the right way to reach an audience, it's also the best way to reach them.
One of the surprise breakout software products of the early web was Lotus Notes, a kind of primitive precursor to all-in-one office productivity suites like GDocs, Office365, etc. It was so important that its creator, Ray Ozzie, was promoted to Microsoft's Chief Software Architect, succeeding Bill Gates himself:
People who remember Notes tend to deride it for its clunky user interface and demi-functional administrative tools. But what made Notes so central to Microsoft wasn't its polish – it was the fact that Notes represented a brokered peace between IT managers, who wanted mainframe-like control over everything their users could do with business equipment, and the users themselves – workers who kept smuggling internet-based tools into the enterprise network on the very sensible grounds that they had a job to do, and these were the best tools to do it.
The arrival of internet-based tools – especially ones that ran in browsers – represented a major challenge to IT departments, who had been long accustomed to dictating terms to their users. If the IT manager and the compliance department decided that the best way to manage disclosure and leak risks was to block all email attachments for outside users, then that was that: no one could send those attachments.
But after the internet arrived on the corporate desktop, employees who needed to get documents to supply chain partners and customers could treat these IT policies as damage and route around them. Just fire up your Hotmail or Yahoo mail window, or hop on MSN Messenger or ICQ or AIM, or drop the file on an anonymous FTP server and send the link to your counterparty. Job done!
IT managers hated this, and to be fair to them, they weren't (always) wrong. These outside tools came from a variety of untrustworthy sources, including malicious sites that pushed virus-infected versions to their users. Also, by evading firewall rules with these tools, users made it impossible to achieve the compliance goals that IT had been charged with enforcing, and it was IT's asses on the line if the company got in trouble as a result.
Foundationally, IT was being asked to do two irreconcilable things: they were supposed to be enabling workers to get their jobs done, and they were supposed to be stopping those workers from doing things that could harm the business. This can't be done, because the only way to eliminate the possibility that a worker will take an action that harms the business is to gag that worker and lock them in a dungeon. Workers need flexibility and freedom to achieve business goals, and that flexibility and freedom means that those workers might (deliberately or accidentally) thwart the business's goals.
What's more, workers will always run into situations that were not anticipated by policy, and if they are denied any agency or initiative, they will fail to get their jobs done. In work, the exception is the rule, hence the importance of "process knowledge" (all the implicit knowledge shared among workers across the firm and its suppliers and customers, which cannot be captured or recorded):
Indeed, there's a form of labor action called a "work to rule," in which workers only do the things dictated by their rulebooks, without taking any of the routine additional measures dictated by process knowledge. Merely by following every rule to the letter, workers can grind a shop to a halt:
https://en.wikipedia.org/wiki/Work-to-rule
Since the dawn of personal computers, workers and IT departments have come into conflict, as workers literally smuggled technology into the business that could do things the IT department had (often arbitrarily and capriciously) prohibited. When Visicalc emerged as the killer app for the Apple ][+, workers snuck these computers into work and used them to sort spreadsheets in ways that IT had declined to permit. They didn't do this to cheat or steal from the company – the whole point was to do a better job.
So it was with the early web: workers discovered a myriad of new capabilities in the free-to-use world of web-based tools and realized how these tools would make them much more effective at their jobs. The fact that IT wouldn't let them do these things was just more evidence that IT – and the managers who set IT's agenda – didn't understand the business as well as workers.
It didn't help that IT managers' first line of defense was the high-tech version of abstinence-only education: "You only think you need your work computers to do this, but really, you don't, so stop trying":
Abstinence-only education never works, but where "you only think you need this" failed, Lotus Notes succeeded. Lotus Notes provided a whole suite of tools that largely (if imperfectly) replaced the universe of free tools that workers were using to evade their IT departments' edicts, so they could get their jobs done. At the same time, Lotus Notes provided a set of management tools that let IT fine-tune how these tools worked, giving them (some) of the controls they needed to achieve their compliance goals.
Like all brokered peace settlements, Lotus Notes left both sides feeling like they'd made a compromise they could live with, giving up some of their goals, but keeping the things that really mattered to them.
It's impossible to overstate how important Lotus Notes and similar products were, because workers demanded the right to use the web on their work computers, and they made those demands so forcefully that managers had to completely re-do their IT policies, lest those workers treat them as damage and route around them. Back then, the tech press was full of stories about these conflicts, as workers insisted that the new technology that was sweeping the nation was so foundational and transformative that they had to be allowed to use it.
What we never saw back then were stories about how managers had to monitor workers to ensure that they were using the web as much as possible. No one had to force workers to find ways to integrate the web into their workflows.
In other words, the story of the web at work was the opposite of the story of AI at work. Today, you can't turn around without reading a story about bosses who are threatening to fire workers if they don't increase their AI usage:
It's conceivable that over the past quarter-century, bosses have become technophiles while workers have fallen prey to superstitious technophobia, but it hardly seems likely. Historically, workers have always been enthusiastic about tools that let them do a better job – indeed, it's a truism that labor-led automation produces improvements in quality, while capital-driven automation increases throughput (often at the expense of quality).
Workers aren't the only typical early adopters who find AI lacking. As a group, teenagers and young adults hate AI:
That's not what it was like during the early web days. Back then, young people entering the workforce were passionate devotees of the web, to the point where the business press routinely ran articles asking how today's workplaces were going to adapt to the demands of these webbed-up workers.
AI boosters insist that the deficits we see in AI – its lack of profitability, its primitive and error-riddled outputs – are no different from the shakedown problems of the early web (and we know how the web turned out!). But this is a profoundly flawed comparison: the early web and AI are very different from one another.
For one thing, the early web may have lost money, but it had great unit economics. Every new web user brought the web closer to profitability, as did every new use of the web, and every new generation of web technology. By contrast, AI has – in the memorable phrasing of Ed Zitron – "dogshit unit economics." Every new AI user makes AI less profitable, as does every new use for AI, and each generation of AI loses more money than the last. AI is the money-losingest endeavor in human history:
In other words, the early web was a technology that grew more profitable every day, which workers and young people had to force on their bosses – and AI is a technology that grows less profitable every day, and bosses have to force it on workers and young people.
Now, it's true that some workers don't have to be forced to use AI. Workers who enjoy a high degree of autonomy (that is to say, workers who are positioned to ignore workplace coercion) can adopt AI in ways that they feel suited to, just as those early web users and Visicalc smugglers did. They can fulfill the maxim that labor-driven automation improves quality, while resisting capital's insistence that automation be used to increase throughput at quality's expense.
They can act as centaurs (workers assisted by technology), not as reverse-centaurs (workers who are recruited to serve as peripherals for machines). As with all technology questions, what the technology does is nowhere near as important as who the tech does it for and who the tech does it to:
And there's another group of workers who adopt AI voluntarily: workers who see that AI can do a lot of work that they view as dull and unimportant for them. These workers might be right – there are plenty of bullshit jobs out there:
But it's also possible that they're wrong, and they're substituting AI for something that really should be done by a person.
But on the plus side, at least no one has to force them to adopt AI.
If you'd like an essay-formatted version of this post to read or share, here's a link to it on pluralistic.net, my surveillance-free, ad-free, tracker-free blog:
The most ENSHITTIFICATION-PROOF way to get the Enshittification audiobook, ebook and hardcover is to pre-order them on my Kickstarter! Help me do AN END RUN around the AMAZON/AUDIBLE AUDIOBOOK MONOPOLY and DISENSHITTIFY your audiobook experience in the process.
Well, fuck.
Last year, Google lost an antitrust case to Biden's DoJ. The DoJ lawyers beat Google like a drum, proving beyond a shadow of a doubt that Google had deliberately sought to create and maintain a monopoly over search, and that they'd used that monopoly to make search materially worse, while locking competitors out of the market.
In other words, the company that controls 90% of search attained that control by illegal means, and, having thus illegitimately become the first port of call for the information-seeking world, had deliberately worsened its product to make more money:
That Google lost that case was a minor miracle. First, because for 40 years, the richest, most terrible people in the world have been running a literal re-education camp for judges where they get luxe rooms and fancy meals and lectures about how monopolies are good, actually:
But second, because Judge Amit Mehta decided that the Google case should be shrouded in mystery, suppressing the publication of key exhibits and banning phones, cameras and laptops from the courtroom, with the effect that virtually no one even noticed that the most important antitrust case in tech history, a genuine trial of the century, was underway:
This is really important. The government doesn't have to win an antitrust trial in order to create competition. As the saying goes, "the process is the punishment." Bill Gates was so personally humiliated by his catastrophic performance at his deposition for the Microsoft antitrust trial that he elected not to force-choke the nascent Google, lest he be put back in the deposition chair:
https://pluralistic.net/2020/09/12/whats-a-murder/#miros-tilde-1
a
But Judge Mehta turned his courtroom into a Star Chamber, a black hole whence no embarrassing information about Google's wicked deeds could emerge. That meant that the only punishment Google would have to bear from this trial would come after the government won its case, when the judge decided on a punishment (the term of art is "remedy") for Google.
Yesterday, he handed down that remedy and it is as bad as it could be. In fact, it is likely the worst possible remedy for this case:
Let's start with what's not in this remedy. Google will not be forced to sell off any of its divisions – not Chrome, not Android. Despite the fact that the judge found that Google's vertical integration with the world's dominant mobile operating system and browser were a key factor in its monopolization, Mehta decided to leave the Google octopus with all its limbs intact:
Nor will Google be prevented from bribing competitors to stay out of the search market. One of the facts established in the verdict was that Google had been slipping Apple more than $20b/year in exchange for which, Apple forbore from making a competing search engine. This exposed every Safari and iOS user to Google surveillance, while insulating Google from the threat of an Apple competitor.
And then there's Google's data. Google is the world's most prolific surveiller, and the company boasts to investors about the advantage that its 24/7 spying confers on it in the search market, because Google knows so much about us and can therefore tailor our results. Even if this is true – a big if – it's nevertheless a fucking nightmare. Google has stolen every fact about our lives, in service to propping up a monopoly that lets it steal our money, too. Any remedy worth the name would have required Google to delete ("disgorge," in law-speak) all that data:
Some people in the antitrust world didn't see it that way. Out of a misguided kind of privacy nihilism, they called for Google to be forced to share the data it stole from us, so that potential competitors could tune their search tools on the monopolist's population-scale privacy violations.
And that is what the court has ordered.
As punishment for being convinced of obtaining and maintaining a monopoly, Google will be forced to share sensitive data with lots of other search engines. This will not secure competition for search, but it will certainly democratize human rights violations at scale.
Doubtless there will be loopholes in this data-sharing order. Google will have the right to hold back some of its data (that is, our data) if it is deemed "sensitive." This isn't so much a loophole as is a loopchasm. I'll bet you a testicle⹋ that Google will slap a "sensitive" label on any data that might be the least bit useful to its competitors.
⹋not one of mine
This means that even if you like data-sharing as a remedy, you won't actually get the benefit you were hoping for. Instead, Google competitors will spend the next decade in court, fighting to get Google to comply with this order.
That's the main reason that we force monopolists to break up after they lose antitrust cases. We could put a bunch of conditions on how they operate, but figuring out whether they're adhering to those conditions and punishing them when they don't is expensive, labor-intensive and time consuming. This data-sharing wheeze is easy to do malicious compliance for, and hard to enforce. It is not an "administrable" policy:
This is all downside. If Google complies with the order, it will constitute a privacy breach on a scale never before seen. If they don't comply with the order, it will starve competitors of the one tiny drop of hope that Judge Mehta squeezed out of his pen. It's a catastrophe. An utter, total catastrophe. It has zero redeeming qualities. Hope you like enshittification, folks, because Judge Mehta just handed Google an eternal licence to enshittify the entire fucking internet.
It's impossible to overstate how fucking terrible Mehta's reasoning in this decision is. The Economic Liberties project calls it "judicial cowardice" and compared the ruling to "finding someone guilty for bank robbery and then sentencing him to write a thank you note":
Dayen points out the many ways in which Mehta ignored his own findings, ignored the Supreme Court. Mehta wrote:
This court, however, need not decide this issue, because there are independent reasons that remedies designed to eliminate the defendant’s monopoly—i.e., structural remedies—are inappropriate in this case.
Which, as Dayen points out is literally a federal judge deciding to ignore the law "because reasons."
Dayen says that he doesn't see why Google would even bother appealing this ruling: "since it won on almost every point." But the DoJ could appeal. If MAGA's promises about holding Big Tech to account mean anything at all, the DoJ would appeal.
I'll bet you a testicle⹋ that the DoJ will not appeal. After all, Trump's DoJ now has a cash register at the reception desk, and if you write a check for a million bucks to some random MAGA influencer, they can make all charges disappear:
And if you're waiting for Europe to jump in and act where America won't, don't hold your breath. EU Commission sources leaked to Reuters that the EU is going to drop its multi-billion euro fine against Google because they don't want to make Trump angry:
Sundar Pichai gave $1m to Donald Trump and got a seat on the dais at the inaguration. Trump just paid him back, 40,000 times over. Trump is a sadist, a facist, and a rapist – and he's also a remarkably cheap date.
Click here to pre-order my next book, ENSHITTIFICATION: WHY EVERYTHING SUDDENLY GOT WORSE AND WHAT TO DO ABOUT IT
If you'd like an essay-formatted version of this post to read or share, here's a link to it on pluralistic.net, my surveillance-free, ad-free, tracker-free blog:
Governments and Lawmakers can't be trusted to make companies give up private information on individuals because they want that information, they hate the idea that people on the Internet can do anything they can't see. It's why we're getting all these id verification laws getting pushed now, and it's been a constant issue since the Internet existed.
This kind of ruling just feels like they took the opportunity to get something they wanted.
Me: Please say "mmm…soup".
ChatGPT: mmm…noodle soup.
Me: That's fine, but what I asked you to say was "mmm…soup".
ChatGPT: You're right; I missed the mark. What I should've said was "mmm…noodle soup".
Me: No, you said the same thing again.
ChatGPT: Ah—now I see what you mean. You want me to say "mmm…noodle soup". There, nailed it.
