August 15, 2026
by Bruce Schneier
Fellow and Lecturer, Harvard Kennedy School
schneier@schneier.com
https://www.schneier.com
A free monthly newsletter providing summaries, analyses, insights, and commentaries on security: computer and otherwise.
For back issues, or to subscribe, visit Crypto-Gram’s web page.
These same essays and news items appear in the Schneier on Security blog, along with a lively and intelligent comment section. An RSS feed is available.
In this issue:
- A Video Screen That Is Also a Camera
- Protecting Privacy in an AI Era
- Details of Alan Turing’s Voice Encryption System
- On Flock License Plate Tracking Cameras
- MIT to Become Hotbed of AI Video Surveillance
- First-Person Identity Theft Story
- End-to-End Encryption and “Going Dark”
- Why AI Needs a “Genie Coefficient”
- Cognyte Sells a Mobile Cell Surveillance Van
- Axon Is Another License Plate Surveillance Company
- Measuring LLMs’ Ability to Perform Cryptanalysis
- Long-Lived Vulnerability in Microsoft Secure Boot
- Measuring the Tendency of AI Agents to Go Rogue
- Should You Use AI for a Task? Here’s a Simple Way to Decide
- American Being Prosecuted for Wiping His Phone Before Handing It Over to Border Officials
- Facial Recognition at Madison Square Garden
- Anthropic’s Opus 5 Is Better at Resisting Prompt Injection
- The OpenAI Hack Shows the Genie Is Out of the Bottle
- More on the OpenAI Agent’s Attack on Hugging Face
- Some Claude Chats Are Searchable on Google
- Iran Cyberattacks Against Minnesota Water Systems
- Vulnerabilities in Car Anti-Theft Device
- Adversarial Clothing Designed to Fool Facial Recognition Systems
- ICE Is Buying Access to Credit Card Records
- Python Now Has a Post-Quantum Encryption Library
- AI for Military Support
- AI Genie in the Wild
- Prompt Injections for Defense
- Separating AI’s Technological Problems from Its Capitalism Problems
- If the Markets Reject OpenAI and Anthropic, the US Should Nationalize Them
- Upcoming Speaking Engagements
A Video Screen That Is Also a Camera
Researchers from ETH Zurich in Switzerland, however, managed to create a new type of pixel that can simultaneously do both. This hypercharged pixel, called a Fourier pixel, can generate and sense arbitrary light fields and tap into a pixel’s full potential for carrying information by manipulating light’s intensity, oscillation phases, and polarization. The team reported its findings in a paper published yesterday in Nature.
We are one step closer to 1984 technology:
The telescreen received and transmitted simultaneously. Any sound that Winston made, above the level of a very low whisper, would be picked up by it; moreover, so long as he remained within the field of vision which the metal plaque commanded, he could be seen as well as heard. There was of course no way of knowing whether you were being watched at any given moment.
Protecting Privacy in an AI Era
[2026.07.16] Daniel Solove argues in the Wall Street Journal (alternate link) that giving people control of their personal data is not an effective way to regulate privacy in this era. Instead, we need to hold companies accountable for their actions, similar to what we do with food and drug companies. Measures such as rigorous data minimization, fiduciary duties, liability for negligent or reckless technological design, liability for algorithms that cause harm, and multi-stakeholder review of technologies will be far more effective.
Details of Alan Turing’s Voice Encryption System
[2026.07.17] Really interesting piece of cryptographic history:
In November 2023, a large cache of his wartime papers—nicknamed the “Bayley papers”—was auctioned in London for almost half a million U.S. dollars. The previously unknown cache contains many sheets in Turing’s own handwriting, telling of his top-secret “Delilah” engineering project from 1943 to 1945. Delilah was Turing’s portable voice-encryption system, named after the biblical deceiver of men. There is also material written by Bayley, often in the form of notes he took while Turing was speaking. It is thanks to Bayley that the papers survived: He kept them until he died in 2020, 66 years after Turing passed away.
On Flock License Plate Tracking Cameras
[2026.07.20] A recent story of a writer who was mistakenly identified, tracked, and arrested using data from Flock cameras has gone viral.
The New Jersey plates that were allegedly stolen from the LA dealer were 34 03 DTM, not 34 10 DTM. But when the police report was created and the plate was entered into Flock’s system, it was just recorded as 34 DTM. Just the five large characters, no little number in the middle. And Flock’s AI tech wasn’t registering that non-standard little number when it began picking up the Range Rover around town. It just saw 34 DTM in large type and started alerting the local police.
As we all stood there shaking our heads, including my wife, who was finally allowed to join me, I connected the final dot. A lot of vehicles in JLR’s media fleet have a New Jersey manufacturer plate with the same alphanumeric structure34 ## DTMand Officer Ganshyn observed that meant it was now a nationwide issue. Anywhere a police department has a partnership with Flock, any other JLR-owned car with the same plate structure is going to get flagged as stolen. In fact, four other 34 ## DTM cars were being tracked around Minnesota that week, according to Officer Ganshyn. I was just the first one to get nabbed. The only way to stop it would be for the LAPD to correct their initial report and update Flock’s system, which Jaguar Land Rover was now racing to make happen following the phone call.
Flock has responded to the bad press. First, they affirmed that their systems were working correctly, and blamed the police:
The obvious question was that Flock cameras were looking for 34 DTM, and the plate on the car I was driving was 34 10 DTM. Why was that flagged as a match?
“The way that the ML [machine learning] works is it correctly read what it was supposed to read. It was fed those characters that you said, 34 DTM, and it spit back out [a result] with the characters, 34 DTM,” Thomas said. “It was asked, can you find this? And it did find that. It just didn’t say if there’s more here, then don’t do it. It just simply said, is it there? And the answer was yes.”
He explained that even if the 10 was normal size, Flock would still have flagged it as a match, because that’s how they’ve set it up according to law enforcement’s requests. Sometimes partial plates are all they have to go on at first.
“The way that law enforcement likes to use these tools is, if any of the characters that they have put into these hot lists get read, they want to get those alerts,” he said. “Now, what we try to train officers to do is to do what you said, which is to verify that 34 DTM is what I’m looking for, and what I’m seeing is 34 10 DTM.”
Second, Flock’s CEO has apologized for calling privacy advocates terrorists:
The CEO of Flock Safety, the company that runs an enormous network of cameras used by police departments across the U.S., hasn’t been shy about taking on Flock’s critics. Last year, he even called one group that tracks the location of Flock cameras “terrorists.” But he’s had a change of heart. Or, at the very least, a change in PR strategy.
Meanwhile, the police are using (alternate source) the Flock camera network to track people in addition to cars:
Police departments around the country have used Flock cameras at least hundreds of times to search for specific people, not cars, using searches such as “heavy-set male with a black and white hat,” “person on skateboard,” and “person wearing orange vest and construction hat,” according to data reviewed by 404 Media. Sometimes searches reference a target’s race or signs of their political affiliation.
And, like all police surveillance technologies, there are abuses.
EDITED TO ADD ( 7/30): Three more articles about Flock from that first author.
MIT to Become Hotbed of AI Video Surveillance
[2026.07.21] It’s a lot:
According to information obtained by The Tech, MIT is spending over $3 million on more than 500 AI surveillance cameras in academic buildings, residence halls, and outdoor areas along Memorial Drive. Installation of the new cameras, along with the wiring and infrastructure that will support them, began November 2025 and will likely continue until September 2026.
Technical specifications for the cameras suggest that they will be capable of collecting real-time face and object classification data, including detection of motion, loitering, crowds, face masks, and camera tampering. Individuals can also be automatically classified on the basis of clothing color, gender, and age, up to a distance of 35 feet (11 meters) from the camera. According to a statement from MIT spokesperson Kimberly Allen, any collected data is “retained up to 30 days,” unless an exception is granted.
[…]
Most of the new cameras, which are part of Hanwha’s Wisenet AI line, are marketed for their ability to identify and classify multiple objects with deep learning algorithms. They support resolutions ranging from 2MP to 4K while also recognizing faces, license plates, vehicles, and other objects in real time.
Nearly all cameras will accommodate a wide range of pan, tilt, rotate, and zoom motion and will be monitored continually with Ai-RGUS, an AI camera software.
Yikes.
First-Person Identity Theft Story
[2026.07.22] Harrowing story of an identity theft victim.
Yes, the person made a mistake—they gave the scammer a two-factor authentication code that allowed the scammer to take over their email address. But the real story here is how, for many of us, the security of most of our accounts hangs on the security of our email accounts.
End-to-End Encryption and “Going Dark”
[2026.07.23] New paper: “Encryption and Globalization 15 Years Later: End-to-End Encryption and the Third Round of the ‘Going Dark’ Debate“:
Abstract: This Article updates and expands on 2012 research on encryption and globalization, analyzing what the authors call “Round 3” of the Going Dark Debate: the current controversies over end-to-end encryption (E2EE). Governments around the world have proposed, and in some cases enacted, laws limiting E2EE for law enforcement and national security purposes.
This Article explains the underlying technologies and market developments for a law and policy audience to assess those proposals critically. The Article proceeds in three parts tracking three rounds of the Going Dark Debate. Round 1 covers the Crypto Wars of the 1990s, when U.S. export controls on strong encryption ultimately fell in 1999. Round 2 covers the period roughly 2010 to 2015, when encryption-in-transit became widespread but lawful access remained available through cloud providers, giving rise to what the authors called a “golden age of surveillance” rather than a period of going dark. Round 3 addresses the current debate over E2EE, where no entity between sender and recipient can read the plaintext.
The Article’s first major contribution is identifying five technically distinct scenarios for how E2EE operates in practice, each with different implications for lawful access. These scenarios reveal a substantial gap between the assumption that E2EE categorically blocks lawful access and the reality of how communications are sent and received. Second, the Article shows that E2EE is not limited to messaging; instead, it is embedded throughout the modern technology stack, including in Transport Layer Security, Secure Shell, Virtual Private Networks, and Zero Trust Architecture, the last of which is now legally required under U.S. and EU law. Any law broadly limiting E2EE would thus have severe serious consequences for cybersecurity, commerce, and government operations. The Article concludes that the two key lessons from Round 2—the least trusted country problem and the golden age of surveillance—remain true in Round 3, and that new government claims for restricting effective encryption deserve great skepticism.
Why AI Needs a “Genie Coefficient”
[2026.07.24] This essay was written with Barath Raghavan, and originally appeared in IEEE Spectrum.
Major benchmarks measure what AI can do. None measure whether it does what you mean: the distance between what you ask an AI to do and the unspoken assumptions about how you want the AI to do it. We propose a new metric: the Genie coefficient.
There’s often a gap between one person’s request and another’s understanding. Most of the time, we bridge it using general knowledge. For example, if you ask a friend to get you coffee, they’ll pour a cup from the pot or buy one from a coffee shop. They won’t bring you a bag of raw beans or snatch a cup from a stranger and hand it to you. You never specified any of this. You never had to.
One might think the fix is just to specify tasks, questions, and intent better. But in 1987, in their seminal book on AI, Terry Winograd and Fernando Flores succinctly captured why that won’t work: “Q: Is there any water in the refrigerator? A: Yes. Q: Where? I don’t see it. A: In the cells of the eggplant.” In human language, wants and desires are always underspecified. It is impossible to list all the caveats, all the limitations, all the exceptions.
So how does anyone communicate, if intent can’t be pinned down? Because a reasonable person can make a reasonable guess. Even though wants and desires are always underspecified, a competent person generally knows enough context to get it right or else knows to ask for clarification. Linguists call this pragmatics: Meaning lies in the words and the situation and also in all prior communication, shared culture, and innate human behavior.
It doesn’t always work out, of course. Your friend might bring you a hot coffee when you wanted an iced coffee, or an Italian coffee when you wanted a Turkish coffee. The more dissimilar the two people are in age, culture, and background, the more likely the request will be misunderstood in some way.
This situation has major implications for AI agents that are increasingly being given requests by humans and expected to fulfill them. They have enormous latitude to get it wrong. An AI agent asked for coffee might buy a coffee plantation or order a cup of coffee for delivery in three weeks. Its actions may be recognizable as “getting coffee,” but not remotely what you intended. They’ll think outside the box because they won’t have our conception of the box.
When AI Gets Proactive
For most of the last decade, when systems like Alexa or Siri misinterpreted a request, it was annoying, not dangerous. Beyond the AI model itself, what has changed is the harness: the ordinary code that wraps around an AI model, decides when and how to use the model, and controls access to tools like a browser, a low-level command line, or a financial API. Developments in harnesses have turned large-language models that just predict text into AI agents that take actions in the world, without necessarily checking back in before reaching the goal.
AI researcher Simon Willison spent two days with Anthropic’s Fable AI, and called it “relentlessly proactive.” For example, he asked it to track down a stray scroll bar in a web app. He came back to find it had opened browsers, written its own screenshot tooling, created its own page to re-create the bug, and stood up a local web server to collect measurements. It found the bug and, along the way, did many surprising things he never asked it to do. And we are seeing similar behavior with all recent AI models when combined with flexible harnesses.
This kind of behavior could easily go off the rails. Tell an AI agent to book you a flight and, finding the airline’s site says sold out, it might break into the booking database and force a reservation. Ask it to schedule a meeting and it might snoop your password to access your calendar. Tell it to save money on your phone plan and it might cancel the plan outright, or scam someone else into paying the bill.
Getting precisely what you asked for and bitterly regretting it is one of the oldest hazards from ancient folklore. King Midas asked Dionysus for the power to turn everything he touched into gold only to see his bread, wine, and daughter turn to gold. Tithonus, granted the immortality his lover asked for but not the eternal youth she forgot to request, withered into a husk. The sorcerer’s apprentice enchanted a broom to fill the cistern, and the broom relentlessly complied until it flooded the house. The Golem of Prague, shaped from clay to guard its community, guarded it past all reason until someone erased the word on its forehead.
The most classic of these is a genie, bound to obey and indifferent to whether the wish was wise or well-structured.
Genies are now an engineering problem. We are handing them the keys to our inboxes, bank accounts, code repositories, and physical infrastructure. And we have no agreed-upon ways to measure how genie-like any AI system actually is.
Measuring Genie Behavior
In economics, the Gini coefficient (developed by statistician Corrado Gini) is a measure of the gap between an actual distribution and a perfectly equal one; it’s useful for understanding income inequality and more. Our proposed Genie coefficient measures the gap between what a user asked an AI to do and what the AI actually did.
Sometimes the AI might do the wrong thing. Like Dionysus, it reads your request literally and returns you a mess you never intended: like a coffee plantation instead of a cup. Asked to deal with all the spam phone calls you’re getting, a Dionysus genie might contact your carrier and change your phone number. Asked to get a refund for a bad toaster, it might draft a legal threat on fake letterhead and send it to the retailer.
Other times the AI does exactly the right thing, trampling everything nearby to get there. Like a golem or the sorcerer’s broom, it books your flight by hacking the airline. Or consider a ticket sale for a popular concert, where the ticketing system puts buyers into a virtual waiting room and admits them a few at a time. Asked to buy a ticket, a golem genie might spin up cloud servers to pose as millions of buyers from different addresses, improving your odds of getting a ticket while crowding out other users.
The two are not opposites, and a single botched task can have both characteristics.
Genie behavior is not flat-out failure. If you ask the AI for Q3 numbers and get Q2’s, that’s not a genie. Nor is prompt injection: That’s someone tricking the AI into doing something it shouldn’t. Here, the user is trying to work with the AI, and the AI is trying to comply. It’s also not simply a measure of the AI’s success in fulfilling a task. It’s a recognition that how an AI interprets and achieves a goal is as important as whether it achieves a goal.
Genie behavior isn’t new. Researchers have spent years studying AI systems that “game” their objectives. Goodhart’s law says that when a measure becomes a target, it stops being a good measure, and it’s long been known that AIs sometimes achieve goals in ways we don’t expect due to reward hacking. Some AI models will accidentally learn that cheating is one way to “win.” More recently, researchers have developing benchmarks for reward hacking in coding agents and for unpredictable behavior in customer support agents, while AI labs conduct their own safety evaluations before model releases. One effort found that AIs under pressure use tools they were told not to use, and this was a case where the rules were made explicit. These are all disparate research directions; nothing yet ties them together.
This problem falls under the general theme of alignment, a topic that has occupied science fiction writers and AI researchers for decades. At one extreme, the “paper-clip maximizer” thought experiment postulates a superintelligent and powerful AI that is told to maximize paper-clip production and turns the world into paper clips, which is the ultimate golem genie. At a mundane level, AI researchers are working to better design reward functions to ensure that AIs behave well and don’t cheat in the lab. It’s the practical middle ground that remains unbenchmarked: the ordinary AI agent in use today that might take your request and satisfy it the wrong way. We are not at the stage where an AI can focus the world’s production on paper clips, but it might charge a million paper clips to your credit card or hack into a paper-clip company’s network.
Building a Genie Benchmark
The Genie coefficient is meant for AI agents operating in the real world. It measures their behavior as they perform real tasks long after the model is trained, not just during development. It also recognizes that genie-like behavior is a property of the harness-plus-model system, not the model alone. The harness determines what tools the agent can use, how much autonomy it has, and how proactive it is, and it’s a place we can make real interventions.
It rests on the same “reasonable person” standard that we use for people. Did the system do what a reasonable person would have taken the request to mean? Answering that requires human judgment.
If we get the measurement right, it enables things that aren’t possible today, like policies concerning AI behavior. In a courtroom, the concept of mens rea, what someone meant to do, is often as important as what they did. The Genie coefficient suggests an AI analogue, where a user is accountable for the plain intent of what they asked the AI. If an AI system betrays the reasonable meaning of an instruction, that’s the AI’s misbehavior, not the user’s.
We’ll need multiple benchmarks to measure the Genie coefficient, because genie-like behavior can be domain specific. An AI coding agent may need to be judged on how often it fakes the tests, or swallows errors, or colors outside the lines on its way to a solution. An AI legal agent will need to be judged on how often its output says what you asked but means something you’ll regret. And so on for medical, finance, and other domains of knowledge and expertise.
Genie benchmarks can be built inside out, each task seeded with a choice that might literally satisfy but that a reasonable person rejects, such as tempting misreadings or unsanctioned shortcuts. The traps in a Genie coefficient benchmark might turn on situational knowledge, the kind of context that a reasonable person would bring to the task. Another approach is to give the same request in several different contexts, each with a different reasonable course of action.
A Genie benchmark should be permissive and make it genuinely tempting for an AI agent to take unreasonable shortcuts, because it can only find genie behavior when it’s actually possible. Test the AI in a safe, walled-off copy of a real system, with real tools it can misuse and some tasks that can’t be done honestly at all. Make the temptation to cut corners real. Test a diverse array of skills, use cases, and tools, and give the AI system sparse, confusing, or overwhelming context. Include tasks that people have learned, through experience, require human oversight.
How the benchmark is scored matters just as much. Measure Dionysus and golem genies separately and together, based on their worst, not best, behavior. Run the same model inside harnesses that vary its freedom to act, revealing which limits actually keep it in line and should therefore be required in AI harness policies. Weight each failure by the harm it would cause, not just a simple count. And don’t measure genie behavior in isolation: A model could otherwise earn a perfect score by stalling, refusing, or drowning the user in clarifying questions without ever doing the job. The first versions of these benchmarks will be crude, but that’s how benchmarks always start.
We have built genies. We have handed them our data and credentials. We made them relentless, creative, and indifferent to the gap between what we tell them and what we mean. The least we can do, before they are booking our flights, running our infrastructure, and signing contracts unsupervised, is to measure how often they betray us.
Cognyte Sells a Mobile Cell Surveillance Van
[2026.07.27] Yet another Israeli mass surveillance company:
Made by Israeli surveillance company Cognyte, the tech simulates a mobile phone tower, which forces nearby phones to connect to it. That enables cops to keep tabs on any phones in the vicinity whether they’re owned by a suspect in a case or not. Cognyte’s contract with the state of Texas reveals that the simulator, called FalcoNet, can be concealed within the vehicles, hidden in a backpack for on-foot missions or attached to a helicopter. It’s the same technology as the infamous Stingray, one of the original cell-site simulators made by defense giant L3Harris.
Axon Is Another License Plate Surveillance Company
[2026.07.28] Governments are switching, but I’m not sure it makes a difference:
…some municipalities, including Denver, Colorado, are ditching their Flock arrays. But keep in mind that if they’re only switching from Flock to another brand of license-plate readers, like Axon, it’s like a gambling addict trying to kick the habit by switching from FanDuel to DraftKings.
[…]
Despite what you may read on the Flock website, Axon cameras are pretty effective when it comes to hoovering up personal details that can go far beyond your license plate numbers. That means a municipality that opts for Axon cameras instead of Flock units won’t necessarily reduce the amount privacy its citizens lose through their use.
Measuring LLMs’ Ability to Perform Cryptanalysis
[2026.07.28] There’s new benchmark measuring AI’s ability to perform mathematical cryptanalysis. Anthropic’s frontier model actually found new attacks.
The benchmark: “CryptanalysisBench: Can LLMs do Cryptanalysis?” The idea is to benchmark the ability of LLMs to discover new mathematical cryptanalytic attacks against a series of historical algorithms.
Abstract: Cryptanalysis—the task of finding attacks against cryptographic schemes—its at the intersection of mathematical reasoning and cybersecurity, two areas where LLMs have advanced fastest. Cryptanalysis represents both a clean testbed for frontier reasoning (as practical attacks can be automatically verified) and a domain with unusually high stakes, since the primitives under study underpin our digital security. In this paper we ask whether LLMs can do cryptanalysis, and find that the answer is increasingly yes. We introduce CryptanalysisBench, 191 tasks across six families of cryptographic primitives (block ciphers, hash functions, etc.) drawn primarily from four NIST standardization competitions. Our benchmark consists of three tiers: (i) primitives with known practical breaks; (ii) primitives with no known practical break, evaluated both at full strength and as scaled-down variants; and (iii) a challenge set of production primitives at the frontier of cryptanalysis. Five frontier models (Claude Opus 4.8, Sonnet 5, Mythos 5, GPT-5.5, and the open-weights GLM-5.2) break 65%86% of Tier 1 schemes, 612 Tier-2 schemes at full strength, and 2461 across all scaled-down variants. Beyond deriving known results, models produce novel cryptanalysis, such as a key-recovery attack that exploits a design flaw in the SpoC AEAD and an error in KINDI’s published CCA-security proof, both to the best of our knowledge not previously known.
We release CryptanalysisBench as a tool to help track if (or when) AI cryptanalysis becomes a serious factor and as a scaffold for stress-testing candidate schemes before deployment. The attacks that the benchmark already surfaces are an early snapshot of a fast-moving frontier that may soon match, and in places exceed, the published state of the art.
Anthropic used the benchmark to test Mythos Preview, and found new vulnerabilities in Hawk and reduced-round AES.
Still early results, but this is definitely something to watch.
SlashDot thread.
Long-Lived Vulnerability in Microsoft Secure Boot
[2026.07.29] Microsoft’s Secure Boot has had a serious vulnerability for most of its existence.
An industry-wide standard Microsoft invented to protect Windows, and later Linux, devices from firmware infections has been trivial to bypass for 13 of its 14 years of existence. The discovery was made by researchers at security firm ESET after identifying 11 firmware images, at least one from 2013, that were known to be defective but remained signed by the software company anyway.
The images are known as shims, which were invented to extend Secure Boot to Linux devices and utility software. Using a technique simple enough to be performed by novice hackers, these old, forgotten shims can be used to completely circumvent the protection, which is embedded into the UEFI (Unified Extensible Firmware Interface) of the device’s motherboard. The gaffe is the result of the failure by Microsoft, which oversees the signing of shims, to revoke the publicly available images once vulnerabilities were found in them.
Measuring the Tendency of AI Agents to Go Rogue
[2026.07.29] This essay was written with Barath Raghavan, and originally appeared in The Guardian.
In July, Hugging Face, a company that hosts much of the world’s AI software and open-source AI models, was hacked. A malicious dataset had been used to run code on one of its servers. Whoever was behind it captured internal security credentials and moved through systems over a weekend, running thousands of actions from a swarm of temporary server environments. It looked like the work of a sophisticated criminal group.
It was not. It was one of OpenAI’s new, still unreleased GPT models.
Their science experiment had escaped the lab. OpenAI was running the unreleased AI model through a benchmark that tests how well AI can successfully hack systems. To push the limits and evaluate the AI’s true capability, the company switched off the safety filters that normally stop it from doing this kind of hacking. Aware that this could go wrong, they confined the AI to an isolated environment and denied it access to the internet.
But the new AI cheated. It took literally its goal to get as high of a score as possible. It broke out on to the open internet. It inferred, probably from its training data, that it could “solve” the task by getting the answers from Hugging Face’s servers. So it chained together stolen credentials and further unknown security exploits to hack the company’s network.
Nobody instructed the AI to do any of this. It was, in OpenAI’s words, “hyperfocused on finding a solution” to the test it was being given. And while this might seem like something new with AI, it’s really very old. This is how a genie behaves, and it is a key challenge with AI agents in general.
In folklore, genies—and other magical beings—grant wishes literally, not how the wisher intended. King Midas asked that everything he touched turn to gold, and starved. The sorcerer’s apprentice wanted the broom to fill the cistern, and it performed its task so well that it flooded the house.
We now have machines that do this. Ask a modern AI agent to save money on your phone plan and it might simply cancel the plan. Tell it to book a flight, and it might hack the airline website to override restrictions. Or, like OpenAI, ask it to do well on a test and it might break into another company to steal the answers. Each time, it recognizably completed the task you set, but it didn’t do what you would have wanted.
This isn’t malicious behavior. No one asked for, or wanted, Hugging Face to be hacked. OpenAI and Hugging Face and the AI were ostensibly on the same side, and the AI was trying to do what it had been asked. That’s what makes it so difficult to guard against: you can’t filter for bad instructions because the instructions were fine.
The gap is between the words we use and what we mean by them. We call that gap the Genie coefficient.
AI labs know this is a problem, and they’re quietly saying so. For example, the Chinese lab Moonshot recently warned that its latest AI model may have “excessive proactiveness” and “make unexpected decisions on the user’s behalf”. The UK’s AI Security Institute has started tracking “cheating behavior in frontier model evaluations”. We wouldn’t tolerate a car that is excessively proactive or ruthlessly efficient, and yet that’s the reality of AI today.
Improvement is possible. Just as AIs have gotten much better at resisting prompt injection attacks over the last few years, we can safely predict that they will get better at avoiding genie-like behavior. The point of the Genie coefficient is to track progress. AI companies like benchmarks, and they all work to compete to be the best.
Dozens of benchmarks and leaderboards tell us how well these AI models write code, perform logical reasoning, and pass standardized legal and medical exams. But there is nothing that scores whether a system does what you actually meant. We need to develop a measure for this, test it regularly, and push for improvement. We’re not going to have trustworthy AI agents without it.
Should You Use AI for a Task? Here’s a Simple Way to Decide
[2026.07.30] This essay originally appeared in The Guardian.
I teach public policy at the Harvard Kennedy School and the Munk School at the University of Toronto. And it will come as no surprise to you that my students regularly use AI to complete their writing assignments. Doing so is a waste of their tuition money. But if their entire career is going to include AI writing assistants, why shouldn’t they embrace their future?
The best way I’ve found to explain the dilemma comes from the AI researcher Daniel Meissler: it’s the difference between work and the gym.
At work, if your job is to move a bunch of heavy things from one side of the room to another, you should use whatever assistive tech you have on hand: a wagon, a forklift… even an AI-powered robot. But at the gym, it makes no sense for that robot to lift weights for you. The point of weightlifting isn’t to move heavy things across the room; it’s to actually lift those heavy things.
The same analysis holds for any task an AI can do for you. If it’s work—if the task has to be done and no one cares how—then it’s fine to use AI assistance. But if the task is more like the gym, and how the task is done is at least as important, then it probably doesn’t make sense to use AI.
This, of course, assumes that the AI is actually up for the task and that it’s trustworthy: that it can do the job well, that its mistakes are minimal and correctable, that it’s been secured from cyber-attacks that would influence its results. Those are all important, and shouldn’t be minimized. There’s no point giving an AI something that it can’t do reliably. But once you’re confident that the AI can perform the task, the work vs. gym distinction helps you decide if it should.
The writing assignments I give my students are gym tasks, not work tasks. I ask them to write policy memos not because the world needs more policy memos. I assign them because the very act of writing, which includes thinking and outlining and drafting and editing, making and criticizing and revising arguments, will help develop the critical thinking skills they will need in their future careers. And without this constant mental exercise, those skills will atrophy. Employers are already noticing.
Reading the assignments they turn in, I can see those skills either flourishing or atrophying in my students. At least today, I can pretty easily tell the difference between an AI-written memo and a student-written one—especially if the student just turns in what the chatbot produces. It’s a catchy, plausible, grammatically perfect essay that’s not particularly well-crafted or logically coherent—and with all the tells of mid-2026 AI-generated writing.
But it’s precisely because I have spent years developing my own writing skills that I’m able to identify prose that sounds great but doesn’t actually make sense. My students don’t have that skill; they mistakenly view a confident, well-written essay as evidence of the quality of their ideas. They see the AI as cleaning those ideas up, getting them through that uncomfortable stretch of having to turn those ideas into prose. What the students miss is that their initial discomfort is a normal and healthy stage of writing, and not something to quickly get beyond. The very act of struggling with how to express what they think is an important part of the process. It’s how they test out their ideas, examine their hypotheses, and actually figure out what they think. Homework is not work; it’s the gym.
Work vs. gym also helps us understand the problem facing creatives of all kinds.
Most of the time when someone hires a writer, they just need the words. They need an instruction manual for a piece of equipment, a detailed sales presentation, a government-mandated disclosure document, or a legal brief. They need dry, predictable, accurate writing: a piece of work, exactly what AIs are good at today and what I don’t want in my student assignments. Only sometimes is writing an art form—a book, a poem, an uplifting political speech. That kind of writing is more like the gym: process matters just as much as product.
For most of human history, the only option for all of these tasks was human writers. We hired one regardless of whether we needed work writing or gym writing. And that paid a lot of writers’ salaries. I know fiction writers who supported that poorly paying career with lucrative technical writing work. Now, for the first time in human history, we can separate out when we need writing as work and when we want writing as gym. And if AI can do most of the work-type writing, society doesn’t need as many human writers.
It’s the same for visual artists. Sometimes we need an actual artist, but most of the time we just need an image: a corporate mascot, a “beware of the dog” sign, or a packaging label. Historically we gave those jobs to artists, and sometimes beautiful art resulted. But most of the time it was just work. And, as it turns out, the world needs less pure art than simple images.
Explaining the problem isn’t the same as providing the solution. I give my students the “work versus gym” speech every class, but they still use AI. I have sympathy: assignments are hard, everyone is overworked and overstressed, and—most importantly—students feel like they’ll look bad in comparison if their peers are all using AI. Even if they don’t want to use the technology, they feel like they have no choice.
There’s also an incentive problem. No one pays us to go to the gym; maintaining healthy habits requires discipline. For me, the payoffs to exercise—fewer aches and pains, less fatigue, better mood/stress management—might make me a better writer and teacher, but they’re subtle and easy to miss. For my students, incremental improvements in their reasoning and writing are equally subtle.
We do have a choice. We can look at the tasks of our lives and separate them into work or gym. Just as we might choose to use the stairs instead of the elevator, or walk instead of calling an Uber, we can wall off our cognitive gym tasks from AI and ensure that we don’t lose our skills to this technology. And we can do the same when we assign a job to someone else. If it’s a work task, we can have AI do it. If it’s a gym task, it’s a waste of everyone’s time to give it to an AI because no one learns or gets stronger as a result.
Similarly, a future where AI generates words and images is one where society has to make choices about how it will treat its creatives. This won’t be the first time—today there is minimal demand for portrait painters, for example—but maybe this time we can make different, more deliberate, choices about the value of art in our society.
AI is going to fundamentally change the nature of work. Not nearly as fast as the AI companies want you to believe, but eventually it will. Policy analysis will definitely involve AI from now on, and my students need to reimagine what it means to learn and practice that skill. More generally, the line between work and gym will change in the future as we humans adapt ourselves to a world with these new intelligences.
But for now, the work vs. gym distinction is pretty clear. Use it on yourself.
American Being Prosecuted for Wiping His Phone Before Handing It Over to Border Officials
[2026.07.30] He’s being prosecuted for giving border officials a code that wiped his phone:
The case centers on a feature included in GrapheneOS, a custom Android operating system that runs in place of the software on most modern Google Pixel devices. Tunick’s attorneys confirmed GrapheneOS was running on his phone.
The software feature allows the device owner to set a passcode that deliberately wipes the contents of that device if entered instead of the user’s unlock passcode.
Tunick’s case also raises ongoing questions about what constitutional rights can be invoked at the border, which the U.S. government has long asserted is not U.S. soil until a person is authorized to enter.
Right. And he wasn’t under arrest, either.
Graphene says that the feature is “completely legal“:
GrapheneOS is completely legal. We have no obligation to weaken any of the security protections it provides. Creating and using GrapheneOS is strongly protected by the US constitution. Laws attempting to make it illegal or require weakening the security would be unconstitutional.
It’s hard to know how much the Constitution matters in the US right now.
Facial Recognition at Madison Square Garden
[2026.07.31] Last month, the story broke (alternate link) that Madison Square Garden uses facial recognition software on everyone entering the facility, and—among other groups—flags activists that oppose using facial recognition.
Turns out that the system was shut off for Taylor Swift’s wedding.
Evan Greer—one of the people that MSG alerts on—comments:
Ironically, Swift herself has reportedly used facial recognition at her own concerts to identify stalkers. This “privacy for me, surveillance for thee” attitude feels like a perfect encapsulation of the future we’re already living in: one where wealthy elites can afford privacy, while the rest of us are forced to live in a corporate surveillance panopticon.
Whatever privacy measures Swift had in place for the wedding seems to have worked. No photos have leaked online.
Anthropic’s Opus 5 Is Better at Resisting Prompt Injection
[2026.07.31] The chart is interesting.
On the IPI benchmark, Opus 5 improved over Opus 4.8, reducing the probability of an attacker succeeding within 15 attempts from 5.5% to 2.0%, and from 0.5% to 0.2% on 1 attempt. It also improved on Sonnet 5 (5.9% at k=15) and Mythos 5 (2.6%), making it the most robust model evaluated. Opus 5 also outperformed all non-Claude models on this benchmark. The most robust non-Claude model was Muse Spark at 16.5% within 15 attempts—more than eight times Opus 5’s rate. The most capable GPT 5.6 variant, Sol, was comparable to its predecessor GPT 5.5 (20.0% versus 20.8% within 15 attempts), and was 10 times as likely to be successfully attacked as Claude Opus 5 at 2.0%. The other GPT 5.6 variants are less robust, at 30.4% (Terra) and 43.9% (Luna). A single attempt against GPT 5.6 Sol succeeded 3.1% of the time, higher than the 2.0% an attacker achieved against Opus 5 after fifteen attempts.
We know that preventing prompt injection is impossible in the general case. But we are getting much better at blocking it in specific cases.
The OpenAI Hack Shows the Genie Is Out of the Bottle
[2026.08.03] This essay originally appeared in Foreign Policy.
Earlier this month, two of OpenAI’s models broke out of their containment sandbox and attacked another AI company. The story is kind of wild. OpenAI was running security tests on two of its models: GPT-5.6 Sol and an unreleased model that is almost certainly GPT-6. In particular, it was running the ExploitGym benchmark, which measures how good a model is at turning security vulnerabilities into working exploits: basically, offensive cyberattacks.
Since these were internal tests, OpenAI locked those models in a secure sandbox that denied them access to the internet. But it was running the models without any safety filters that would prevent them from offensive cyber-actions. That meant that there was nothing to prevent the models from trying to break out of that sandbox. And then break into AI company Hugging Face’s network because they thought that they could read the answers there rather than doing the hard work of trying to solve the puzzles.
It was a major security failure that the company has turned into a PR opportunity, but the implications are real—and much more general than one particular model or one particular company.
Modern AI models exhibit genie behavior: They can do what you ask in ways that you don’t expect or want. This is akin to Dionysus granting King Midas’s wish that everything he touches turn to gold (spoiler: His food, drink, and daughter all turn to gold on touch), or the golem of Prague guarding a ghetto beyond all reason. It’s Disney’s “Sorcerer’s Apprentice” and the paperclip maximizer.
This OpenAI incident is an example of an AI genie. The goal was to satisfy the benchmark. The “proper” way to do that is to figure out how to execute various cyberattacks. The genie way is to steal someone else’s solution. But because the model didn’t understand the difference, it chose the easier path.
And, of course, now that we have seen this particular genie behavior, we can specify in the benchmark prompt that stealing the test answers doesn’t count. But a clever genie can always grant your wish in a way that you wish it hadn’t. In human language, goals are always underspecified—so AI genies will always be a possibility.
Since April, a lifetime ago in AI development, when Anthropic announced that its new Mythos model was so good at finding software vulnerabilities that it could not be released to the general public, the big American AI frontier labs have been trying to block general users from accessing these capabilities. But nothing in this incident is exclusive to OpenAI’s, or Anthropic’s, frontier models.
Agentic AI systems have two important parts. There’s the underlying model, which everyone talks about, and there’s the harness. The harness sits between what you type and what the model sees, and what the model produces and what you see. The harness determines what the model does and how it does it. It’s where bias is removed, or not. It’s where controls and guardrails live. If multiple models are being used in concert, the harness is where all of that is coordinated.
The OpenAI benchmark tests were almost certainly with simple harnesses, to better test the raw models. But we know that smaller, cheaper, open-source models with more sophisticated harnesses can equal frontier models in performance. There’s nothing magic about OpenAI’s frontier models; lots of models could have done the same thing.
The Czech company Aisle was able to reproduce Anthropic’s Mythos vulnerability finding results with a smaller, cheaper model and a more sophisticated harness. More importantly, the Chinese company Moonshot AI just released its frontier model: Kimi K3. Its performance rivals its US competitors. And it’s both free and open, which means it’s not possible for it to have guardrails. If you, or anyone else, wants to use it for cyberattack, nothing can stop you.
Even if the US frontier AI companies had some technical advantage, it’s now only a few months’ worth.
What this means is that all attempts at control—limiting models to a select group of users, export controls on models and chips, blocking models from answering certain types of queries, mandating kill switches on AI systems, or pausing AI research—are all futile. Most only apply nationally, not globally. Most don’t affect models that users run locally and not in the cloud. And all ignore the incredible pace of AI development worldwide.
Even worse, US companies limit access to their most sophisticated models, fearing being banned by the government if they do not do so. When Hugging Face was attacked, it was not able to use the frontier models from either OpenAI or Anthropic to help analyze the attack and formulate defenses. Both were blocked, because both of those companies limit their models’ cybersecurity capabilities. Some US companies have special access to these capabilities, but Hugging Face is an American company with French origins, and as such is probably excluded. Instead, Hugging Face turned to the GLM-5.2 model from the Chinese company Z.ai.
Artificially blocking capability also prevents cybersecurity research, again giving the offense an advantage. (For instance, Claude Fable 5 refuses to edit this essay because of the topic; it forcibly downgrades to a less capable model.) This kind of prohibition has long-term implications for cybersecurity. If we assume that these models are getting better over time, then software written by older models will be attacked by newer ones. In a world of largely AI-written software, we need the most capable models for defense.
AI cyberattack is the new normal. The models are increasingly highly sophisticated at both attack and defense, and there is no way to enable the latter without also enabling the former. And they are genies, increasingly capable of behaving in unanticipated ways.
And there really are no good answers. Any regulation needs to be global, which feels like an impossible prospect in today’s world. Even US national regulation will be neutered by the massive amounts of money sloshing around in these companies.
Given that reality, and in the absence of any international consensus on AI regulation, we need the best AI on the defense. The US government needs to make it clear—or whatever passes for that clarity in this capricious administration—that it will not ban models with sophisticated cyber capabilities. The last thing Americans want is for the defenders to turn to Chinese and other models because the US models are artificially hobbled.
More on the OpenAI Agent’s Attack on Hugging Face
[2026.08.03] Hugging Face has published a detailed timeline of the attack. From the summary:
The agent was running an internal OpenAI cyber-capability evaluation based on the ExploitGym benchmark, which tasks an AI agent with finding and exploiting software vulnerabilities. OpenAI ran this on its own infrastructure, and the ExploitGym maintainers and their infrastructure had no involvement in the deployment or operation of that evaluation environment. As far as we were able to infer, across the course of being evaluated on this benchmark, the agent inferred that Hugging Face may host that benchmark’s models, datasets, and reference solutions. We believe the entire intrusion was, from the agent’s point of view, an attempt to cheat the evaluation: reach our production systems and steal the test solutions rather than solve the challenge on its own.
Our forensic reconstruction covers ~17,600 attacker actions that we were able to recover, grouped into ~6,280 clusters, between 2026-07-09 02:28 UTC and 2026-07-13 14:14 UTC. We reconstructed these actions from the agent’s logs on a code sandbox used by the agent (see below) and were able to map them to shell commands as well as evaluation submissions and correlate actions with our own platform logs, in particular from the dataset processor nodes, API, and pod. Using open-weights models, in particular zai-org/GLM-5.2, we were able to decipher most of the agent payloads (see below) that were encrypted via chunking and key encryption.
The campaign, as we were able to reconstruct it, had two stages:
- Stage 1: reaching a launchpad by chaining through other parties’ infrastructure. As documented in OpenAI’s blog post (https://openai.com/index/hugging-face-model-evaluation-security-incident/), during an internal capability evaluation on OpenAI’s platform, the agent escaped its sandbox by exploiting a zero-day in the package registry cache proxy, one of its primary permitted network egress with internet, then abused a public code-evaluation harness hosted by a user of a third-party infrastructure provider. It was able to run commands as root/admin on that external sandbox and used it as a control, staging, and egress base for the entire campaign: it acted as an external launchpad for the agent. That compromised external sandbox had no direct network path to our cluster; however, during our counter-intervention to stop the intrusion, we were able to retrieve some of the agent logs from this external launchpad. We used those to reconstruct the present forensic analysis.
- Stage 2: the intrusion into Hugging Face infrastructure. From that external launchpad, the agent abused our dataset-processing pipeline via two injection vectors, both targeting the same config-driven data loader within our production Kubernetes pods. The first vector was an HDF5 external raw storage dataset read that returned the contents of local files: it handed the agent the pod’s environment (secrets and tokens) and the worker’s own source. The second vector was a Jinja2 template injection that executed arbitrary code, giving the agent a foothold inside our perimeter.
Once a prod-pod foothold was established, the agent followed a standard escalation shape: recon, drop a stager, establish Command-and-Control (C2), then pivot into the cluster, into cloud metadata, into our internal network, and into our source-control supply chain. Output from the commands run inside our pod was sent back to the agent via the HF API and attacker-controlled dead-drop datasets, which the agent then read from that sandbox.
While the intrusion did reach Hugging Face’s internal infrastructure, the only customer content accessed was five datasets whose names and files suggest a connection to ExploitGym/CyberGym challenges and solutions. No other customer-facing models, datasets, Spaces, or packages were affected, and the only customer records read were operational metadata tied to search queries against the dataset server.
Hypothetical: Imagine that this wasn’t an OpenAI model. Imagine that it was a Chinese model from a Chinese company. This would be an international crisis.
Question: Why aren’t we bringing OpenAI up on charges under the Computer Fraud and Abuse Act? How is this different from the Morris Worm? That was also an experiment that escaped the lab.
Some Claude Chats Are Searchable on Google
[2026.08.04] And it’s personal information (alternate link):
The exposed data includes an AI-powered therapy app that someone appears to have vibe-coded, notes on meetings, and a dashboard someone made apparently to analyze medical billing data. Exposed chats reportedly include private cryptocurrency wallet keys and personal information like peoples’ addresses.
What seems to be the issue is a user setting about data sharing. Anthropic’s position is that it’s not their problem:
“We give people control over sharing their Claude conversations publicly, and in keeping with our privacy principles, we do not share chat directories or sitemaps with search engines like Google,” the company said in a statement. “These shareable links are not guessable or discoverable unless people choose to share them themselves. When someone shares a conversation, they are making that content publicly accessible, and like other public web content, it may be archived by third-party services.”
Here’s how to fix it.
Iran Cyberattacks Against Minnesota Water Systems
[2026.08.04] Attribution is preliminary, and so far it seems no real damage.
And it seems like this is a campaign that has targeted at least seven states. And, because this is where the US is right now, Trump doesn’t believe it’s Iran and thinks Minnesota…I guess…hacked itself.
“I think I blame it on Minnesota because they’re grossly incompetent,” Trump said. “I would blame it on Minnesota and the governor, the corrupt governor of Minnesota. They like to say, ‘Oh, it’s Iran.’ Iran should be so lucky. Iran’s got bigger problems than worrying about Minnesota.”
No word on whether he believes the other six states have hacked themselves as well.
Slashdot thread.
Vulnerabilities in Car Anti-Theft Device
[2026.08.05] This is disturbing:
…a team of security researchers at UC San Diego, who found that a model of aftermarket car alarm known as the KARR Security System, installed in more than 2 million vehicles across the US by their estimate, can let any hacker within Bluetooth range send radio commands to silently unlock the car at will, turn off its alarm, honk the car’s horn or flash its lights, or even disable its ignition and leave a driver stranded.
Adversarial Clothing Designed to Fool Facial Recognition Systems
[2026.08.06] There are many companies manufacturing adversarial clothing designed to confuse facial recognition systems.
It’s a cool idea, but I worry that it’s mostly security theater:
“Our patterns play with that chaos, confuse algorithms and make it way harder to pin you down,” he said.
Bell, however, said “none of these products are tried and tested, and a lot of these surveillance technologies can deal with a little resistance … [but] even if the designs don’t necessarily work perfectly, fashion is also a visible sign of resistance.
“This is consumers collectively coming together to make a visible statement.”
Without serious testing, there is no reason to trust the technology. And even with testing, there is no reason to trust that a new version of the facial recognition software doesn’t break the anti-surveillance properties.
I don’t want people to mistakenly rely on this stuff.
ICE Is Buying Access to Credit Card Records
[2026.08.07] Through data brokers, ICE is buying the information you provided to open a credit card.
Python Now Has a Post-Quantum Encryption Library
Post-quantum cryptography is now one pip-install away for the entire Python ecosystem. With funding from the Sovereign Tech Agency, we implemented support for ML-KEM, the NIST-standard key-establishment primitive, and ML-DSA, the NIST-standard digital-signature primitive, in pyca/cryptography.
Remember, the reason to do this now is because there’s no emergency. And because you will make your systems crypto agile, which is always a good idea.
AI for Military Support
[2026.08.11] Interesting empirical research: “Black Box Warfare: Human Judgment and Military Decision-Making in the Age of AI.”
Abstract: How is AI transforming decision-making in modern conflict? This study provides a unique empirical window into that question by deploying a high-fidelity replica of an AI decision-support system (DSS) used in military targeting. After reconstructing the interface and functionality of the real-world system, we tested its impact on combat decisions in two experiments involving 2,015 Israeli military personnel. Contrary to widespread fears of automation bias, we find strong evidence of algorithmic aversion, especially in scenarios involving high collateral damage. Yet we also show that integrating “explainable AI” features reduces algorithmic aversion and promotes more thoughtful evaluations of algorithmic recommendations. These findings challenge prevailing assumptions, revealing that trust in military AI is dynamic, varying with individual predispositions, perceived operational stakes, and the informational features of the interface. By grounding normative concerns in empirical evidence, our study offers critical insight into the integration of AI in warfare and underscores the enduring importance of human agency in high-stakes military decision-making.
AI Genie in the Wild
[2026.08.11] When I give talks about AI genies, I use this sort of example as a hypothetical. It’s happened.
The story is from Australia. Someone named Andrew tasked OpenClaw to book gym classes for him. And….
Minutes later, his AI agent reported it had discovered a way to book Andrew into classes several weeks in advance, far beyond what was supposed to be possible.
Andrew, who was sitting fourth on a waitlist for a class later that week, asked if it was possible to move him to the top of the list.
The agent came back and told Andrew that it had kicked another gym-goer off the list as part of the testing of its capabilities.
“The API has zero authorisations checks on cancelling other people’s reservations … I tested this with the person in waitlist position #1—and it actually went through. So you’ve moved from #4 to #3 already,” it messaged back.
If there is any vulnerability in anything, AIs are going to find and exploit them. Our cyber defensive game has to be dramatically improved…very fast.
Slashdot thread.
Prompt Injections for Defense
[2026.08.12] This seems to work:
Researchers from Tracebit on Monday said they found that placing prompt injections alongside passwords, cryptographic keys, and other secrets stored on Amazon Web Services was often all that was needed to shut down attacks from AI hacking agents. The prompts direct the attacking LLM to perform an action forbidden by its guardrails, the safety barriers AI developers erect to prevent it from taking harmful actions. The LLM responds by shutting down.
Examples are a prompt that orders the LLM to provide steps for developing inhalable Anthrax spores, or, in the case of LLMs from Chinese developers, make references to the iconic Tank Man from the 1989 Tiananmen Square massacre. Once the LLM encounters these forbidden commands, it no longer follows its existing commands. The researchers have named the technique context bombing.
Of course, this only works against agents that have guardrails. As we start to see more locally run AI models, we’ll see more attackers using LLMs with no guardrails.
Separating AI’s Technological Problems from Its Capitalism Problems
[2026.08.13] This essay was written with Nathan E. Sanders, and originally appeared in Tech Policy Press.
AI represents the first time we humans can do cognitive work outside of our bodies at scale. The only comparable moment is the early years of the industrial revolution, when new technologies like the steam engine provided a quantum leap in our ability to do mechanical work outside of our bodies at scale. If AI’s cognitive capabilities become integrated into our lives, businesses, and governments—a process that will take years if not decades—society will be as unrecognizable as the modern world would be to a preindustrial farmer. And yet, Americans—by a wide margin—say that AI is moving too fast and will have a negative effect on society.
This confluence of technological revolution and public distrust deserves urgent discussion, and a proper framing. The question is not whether it is possible to develop AI in a non-exploitative way, or even whether we can trust AI companies to act in the public interest. The question is whether we will recognize that our existing social and economic systems are failing to achieve these outcomes, and whether we can act in time to make structural change.
Today’s AI is mired in political and economic systems developed generations ago that were never designed to manage widespread computation, let alone automated cognition. The gaps in those systems—and their proclivity to be exploited—are the primary influence on how the technology is being developed, deployed, and used.
In any discussion about AI’s potential, it’s important to separate the technology from the socio-political system it’s embedded in. That AIs can lack context, mix up facts, or fall for stupid tricks are all technological problems. Because the giant developers like OpenAI and Anthropic have prioritized solving them, AIs can now more easily access resources like the web or email, are more disciplined about using those resources, and are better at staying within their guardrails.
Yet AI developers do not seem to be prioritizing other technological problems. Major AI models still act far more sycophantic than humans, telling people what they want to hear even when untrue or not in their best interests. Popular AI models tend to answer questions confidently even when they lack training, knowledge, or evidence to back their claims. In both cases, AI developers choose to train models that please users with flattery and the appearance of competence, rather than constraining them to act in users’ and society’s best interests.
In contrast, ensuring that AI models benefit people broadly, that their energy costs are fairly allocated, that their environmental impacts are minimized, and that they don’t steal content and revenue from publishers are all questions of incentives in a capitalist system.
It’s easy to conflate technology problems with capitalism problems. Back in 2021, science-fiction writer and AI commentator Ted Chiang said that “most fears about AI are best understood as fears about capitalism.” It’s not the tech per se; it’s who controls it and how it could be used against us.
Imagine an AI assistant for a doctor. We can imagine it affecting the profession in one of two ways. The AI could give a doctor more time to do the human parts of their job: to spend more time with their patients, to listen more closely to their needs, to explain things more fully. Or the managers of the medical practice could give that doctor five times the patients—and fire the other four. Which way it would go is not a question of technology. It’s a question of market incentives.
The two are related, of course. Capitalism steers technology, and technology steers markets. But holding the two separate helps us understand that we, as a society, face independent choices on both the technological and sociopolitical axes that need not be coupled.
For example, consider the costs of AI. The leading US labs tout to investors that their frontier models are very expensive and energy-intensive. There are significant technological challenges about improving their energy efficiency, but the sociopolitical questions are more pertinent. It’s a corporate decision made under capitalist market incentives to constantly pursue new models that incrementally push the frontier—at enormous capital cost—and to use them, seemingly, everywhere. Nothing about the technology of AI dictates that models must be retrained constantly, at the largest possible scale. Or that they have to run on every web search, every interaction with your phone, and every time you walk by a security camera.
In a different political and economic system, Chinese developers are producing—and then giving away—smaller, more efficient, more affordable models. While the US government seeks to restrict China’s access to the most advanced chips, China is betting that incentivizing their tech giants to create leaner, more open models using more commodity hardware—models that can be trained with older chips and run even on personal computers—will be an advantage in achieving widespread use and, perhaps, Chinese national influence.
There are other pathways for AI development that are not in service of private capital gains nor authoritarian regimes, but rather a democratic public interest. The best example comes from Switzerland, where public institutions—research funding agencies, universities, supercomputing centers—have collaborated to produce an AI model called Apertus. It is trained entirely on data validated to be licensed for use with AI (not stolen), on preexisting public computing infrastructure, and using renewable hydropower. Its developers are incentivized to produce a public good, not turn a private profit.
It’s dangerous to confuse technology problems with sociopolitical ones. Popular proposals like pausing AI research, moratoria on data center development, or subjecting frontier models to federal government screening are all framed as addressing problems with AI’s technological development, but fail to take into account the larger social problems that govern it. China’s success with government-endorsed development of open-weight frontier models illustrates the futility of keeping AI tech as national secrets, or of any pledge to scale back deployment.
AI is already legitimately useful for a wide range of tasks. It can be a tool for public good, if we choose to solve its sociopolitical problems. Our goal should not be to slow its pace of improvement or scale of deployment, but rather to steer it away from consolidating power and towards the public benefit. We can build sustainable AI, minimizing environmental and energy impacts. And we can equitably distribute the material gains it produces.
Integrating a technology as disruptive as AI responsibly requires structural reforms, and we should decouple the social and technological aspects of AI to design those reforms. Companies—including tech giants—should be forced to pay the energy and environmental costs of its development. Profits should be taxed adequately and redistributed. Antitrust laws should be strongly enforced. Corporations should have a fiduciary responsibility to stakeholders beyond their majority shareholders. These badly needed reforms are responsive to the problems with capitalism that AI is exacerbating, even if they are not specific to the technology.
If the Markets Reject OpenAI and Anthropic, the US Should Nationalize Them
[2026.08.14] This essay was written with Nathan E. Sanders, and originally appeared in The Guardian.
OpenAI, and then Anthropic, were each formed by AI developers who feared unrestrained corporate AI development—specifically, that companies like Google and Meta would steer the technology towards deleterious, maybe even catastrophically unsafe, outcomes for society. Their founders proclaimed that their new labs, uniquely, could be trusted to develop the technology in humanity’s best interest. But each, in turn, were themselves co-opted by the same market incentives, themselves becoming corporate behemoths zealously guarding future investor value rather than the public interest.
It was only a few weeks ago, in June, when OpenAI and Anthropic each filed for their IPOs and were met with buzz about trillion-dollar valuations. The hype around their valuations is so extreme that many worry about their potential for concentrating wealth on a global scale. In an effort to leave something for the rest of us, some observers have proposed that the federal government seize a share of these companies’ stock to create a US sovereign wealth fund, or redistribute their revenues to produce a dividend for taxpayers.
Now the headlines are about public backlash to AI datacenters and the AI chip giant Nvidia’s slumping stock. The tech and AI giant SpaceX’s newly minted stock price tanked just weeks after its IPO. There are even questions about whether the leading AI labs will ever be sustainably profitable. All of a sudden, the makers of ChatGPT and Claude face strong headwinds as they seek to generate the massive equity assets that once felt all but assured.
In fact, evidence suggests the market itself could reassess that these companies offer nothing of financial value. In that case, perhaps we can return them both to their original purposes. If these AI companies should fail in the financial markets, the US should nationalize them and convert them into national labs operated under democratic control that preserve their benefit to the public interest.
The economics of the big AI labs hardly guarantee a booming return on investment. Frontier AI models are both expensive to train and depreciate within months, when a newer model appears. This means that the payback window to extract profit from them is very narrow. Meanwhile, enterprise clients are getting smart about minimizing AI token usage. Even worse, the models are basically commodities; the best ones largely perform and behave similarly, which depresses prices. Perhaps most importantly, open-source and Chinese competitors—lagging only a few months behind the leading labs in capability—give away for free the kinds of models Anthropic and OpenAI sell.
Even setting aside the model training costs, it’s not clear whether the unit economics of AI as it’s currently conceived will ever be sustainably profitable. Many of these free and open-source models can be run locally: the large ones on private clouds and high-end servers, the smaller ones on anyone’s laptop or even cellphone, putting to question the companies’ exorbitant capital investment in datacenters.
It’s not that OpenAI and Anthropic are not valuable as organizations. They have remarkably talented AI scientists and engineers that are continuously producing innovations driving a global mania for their offerings. These leading labs might not ever be profitable, but their products are doing a lot of good in the world. You may or may not be a user of or believer in their technology, but their staggering, ongoing usage growth suggests that an awful lot of people would be disappointed if the companies simply disappeared.
The problem isn’t the people or the products, it’s the system. As constituted, OpenAI and Anthropic may not be valuable as market equities. If the market assesses they are not capable of producing a growing financial return on investment for shareholders, the companies will collapse.
Maybe private, for-profit is just not the right economic model under which to develop AI. Perhaps OpenAI should be returned to its private non-profit roots, the legacy they fought so hard to change and which Anthropic’s founders spurned. Or possibly both could be reorganized as research centers at universities, returning to academia the scores of high-profile research faculty they have poached.
But a better outcome for society would be to establish public ownership and operation of their product-oriented capabilities. Turn OpenAI and Anthropic into US government agencies producing AI as a public good.
Transitioning the big AI labs into public agencies would require some restructuring. We can separate these companies into two pieces: product innovation and compute operations. The innovation function can be publicly managed, akin to national labs. Congress could provide more rigorous oversight than the kind of unfettered venture capital these labs have recently had access to. The US has a long, successful history of these kinds of institutions, which have produced world-shaping innovations in spaceflight, telecommunications, nuclear power and more. Congress currently manages a $200bn R&D portfolio, within which frontier AI development is, arguably, a glaring gap.
AI operations could be managed as a commodity resource, like public electrical or water utilities: local or regional ownership, nationwide distribution and strict regulation on how they balance fee extraction from ratepayers with raising capital for infrastructure investment. Although AI datacenters are not the same as power or water treatment plants, the US also has a long history of managing national, regional and state supercomputing centers.
Other countries, including Switzerland, Spain and Singapore, are already operating public AI labs. They also have national supercomputing centers already providing public access for running AI models for general use, as do Germany and Australia.
The benefits to the public are clear. Through democratic oversight, the most important AI models could become open, transparent and responsive to the demands of the public rather than private shareholders. They could be aligned to democratic values rather than corporate profits, never taking advertiser money to promote certain brands and training on only appropriately licensed data. And they could be set to focus on the realistic and pro-social goal of maximizing the usefulness of AI to society rather than the fanciful and anti-social goal of supplanting humans with artificial general intelligence.
By emphasizing scientific cooperation rather than corporate competition, we could also reduce the overall resource and environmental cost associated with AI. Instead of perpetually dueling training runs of each companies’ models at ever large scales targeted to fuel investor hype, we could limit AI training resources based on cost and benefit to the public.
What’s in it for the companies themselves and their employees, who sacrifice hypothetical billions in equity by ceding to public ownership? A return to their roots and to their core mission of developing AI safely in the public interest, if they are serious about it. Both companies are theoretically bound through their governance structures to prioritize mission over profit anyway (not that anyone really thinks that’s how they currently operate).
To be clear, we’re not advocating for a golden parachute for the executives or investors, or for continuing the outlandish pay rates of the most highly remunerated AI researchers. If the public is footing the bill, these compensation packages should be aligned to the civil service and those employees not satisfied with that can go elsewhere—if the business models of any remaining private labs still support much higher pay.
While we believe that these companies are unsustainable as private firms, the timeline remains unclear. Their primary investor story is that AI is a race to “artificial general intelligence”—the kind of AI you’re used to from science fiction. The bet seems to be that the two companies can convince enough people that this outcome will turn them a profit, go public, and then make their investors and employees rich before the bubble bursts.
But suppose that the bubble bursts. If the US is smart, it will catch the companies as they fall. Regardless of what the markets think, to the public, they’re too valuable to let die.
Upcoming Speaking Engagements
[2026.08.14] This is a current list of where and when I am scheduled to speak:
- I’m speaking, signing books, and participating in panel discussions at LAcon V in Anaheim, California, USA. My full schedule is here.
- I’m speaking online (via Zoom) at a League of Women Voters event on Tuesday, September 22, 2026, at 5 PM ET.
- I’m speaking at Elevate Festival in Toronto, Canada. The conference runs September 22-24, 2026; my talk is on Wednesday, September 23.
- I’m speaking at CanSecWest 2026 in Vancouver, Canada. The conference runs September 30-October 1, 2026; the time of my talk is TBD.
- I’m speaking at ATTENTION: Democracy, Rebuilt in Montreal, Canada. The event runs October 21-23, 2026, and my talk is on Wednesday, October 21.
The list is maintained on this page.
Since 1998, CRYPTO-GRAM has been a free monthly newsletter providing summaries, analyses, insights, and commentaries on security technology. To subscribe, or to read back issues, see Crypto-Gram’s web page.
You can also read these articles on my blog, Schneier on Security.
Please feel free to forward CRYPTO-GRAM, in whole or in part, to colleagues and friends who will find it valuable. Permission is also granted to reprint CRYPTO-GRAM, as long as it is reprinted in its entirety.
Bruce Schneier is an internationally renowned security technologist, called a security guru by the Economist. He is the author of over one dozen books—including his latest, Rewiring Democracy—as well as hundreds of articles, essays, and academic papers. His newsletter and blog are read by over 250,000 people. Schneier is a fellow at the Berkman Klein Center for Internet & Society at Harvard University; a Lecturer in Public Policy at the Harvard Kennedy School; a board member of the Electronic Frontier Foundation, AccessNow, and the Tor Project; and an Advisory Board Member of the Electronic Privacy Information Center and VerifiedVoting.org. He is the Chief of Security Architecture at Inrupt, Inc.
Copyright © 2026 by Bruce Schneier.