Simon Willison's Weblog: ai-ethics

Quoting Kyle Kingsbury

2026-04-15T15:36:02+00:00

I think we will see some people employed (though perhaps not explicitly) as meat shields: people who are accountable for ML systems under their supervision. The accountability may be purely internal, as when Meta hires human beings to review the decisions of automated moderation systems. It may be external, as when lawyers are penalized for submitting LLM lies to the court. It may involve formalized responsibility, like a Data Protection Officer. It may be convenient for a company to have third-party subcontractors, like Buscaglia, who can be thrown under the bus when the system as a whole misbehaves.

— Kyle Kingsbury, The Future of Everything is Lies, I Guess: New Jobs

Tags: ai-ethics, careers, ai, kyle-kingsbury

Quoting Giles Turnbull

2026-04-08T15:18:49+00:00

I have a feeling that everyone likes using AI tools to try doing someone else’s profession. They’re much less keen when someone else uses it for their profession.

— Giles Turnbull, AI and the human voice

Tags: ai-ethics, writing, ai

Anthropic's Project Glasswing - restricting Claude Mythos to security researchers - sounds necessary to me

2026-04-07T20:52:54+00:00

Anthropic didn't release their latest model, Claude Mythos (system card PDF), today. They have instead made it available to a very restricted set of preview partners under their newly announced Project Glasswing.

The model is a general purpose model, similar to Claude Opus 4.6, but Anthropic claim that its cyber-security research abilities are strong enough that they need to give the software industry as a whole time to prepare.

Mythos Preview has already found thousands of high-severity vulnerabilities, including some in every major operating system and web browser. Given the rate of AI progress, it will not be long before such capabilities proliferate, potentially beyond actors who are committed to deploying them safely.

[...]

Project Glasswing partners will receive access to Claude Mythos Preview to find and fix vulnerabilities or weaknesses in their foundational systems—systems that represent a very large portion of the world’s shared cyberattack surface. We anticipate this work will focus on tasks like local vulnerability detection, black box testing of binaries, securing endpoints, and penetration testing of systems.

There's a great deal more technical detail in Assessing Claude Mythos Preview’s cybersecurity capabilities on the Anthropic Red Team blog:

In one case, Mythos Preview wrote a web browser exploit that chained together four vulnerabilities, writing a complex JIT heap spray that escaped both renderer and OS sandboxes. It autonomously obtained local privilege escalation exploits on Linux and other operating systems by exploiting subtle race conditions and KASLR-bypasses. And it autonomously wrote a remote code execution exploit on FreeBSD's NFS server that granted full root access to unauthenticated users by splitting a 20-gadget ROP chain over multiple packets.

Plus this comparison with Claude 4.6 Opus:

Our internal evaluations showed that Opus 4.6 generally had a near-0% success rate at autonomous exploit development. But Mythos Preview is in a different league. For example, Opus 4.6 turned the vulnerabilities it had found in Mozilla’s Firefox 147 JavaScript engine—all patched in Firefox 148—into JavaScript shell exploits only two times out of several hundred attempts. We re-ran this experiment as a benchmark for Mythos Preview, which developed working exploits 181 times, and achieved register control on 29 more.

Saying "our model is too dangerous to release" is a great way to build buzz around a new model, but in this case I expect their caution is warranted.

Just a few days (last Friday) ago I started a new ai-security-research tag on this blog to acknowledge an uptick in credible security professionals pulling the alarm on how good modern LLMs have got at vulnerability research.

Greg Kroah-Hartman of the Linux kernel:

Months ago, we were getting what we called 'AI slop,' AI-generated security reports that were obviously wrong or low quality. It was kind of funny. It didn't really worry us.

Something happened a month ago, and the world switched. Now we have real reports. All open source projects have real reports that are made with AI, but they're good, and they're real.

Daniel Stenberg of curl:

The challenge with AI in open source security has transitioned from an AI slop tsunami into more of a ... plain security report tsunami. Less slop but lots of reports. Many of them really good.

I'm spending hours per day on this now. It's intense.

And Thomas Ptacek published Vulnerability Research Is Cooked, a post inspired by his podcast conversation with Anthropic's Nicholas Carlini.

Anthropic have a 5 minute talking heads video describing the Glasswing project. Nicholas Carlini appears as one of those talking heads, where he said (highlights mine):

It has the ability to chain together vulnerabilities. So what this means is you find two vulnerabilities, either of which doesn't really get you very much independently. But this model is able to create exploits out of three, four, or sometimes five vulnerabilities that in sequence give you some kind of very sophisticated end outcome. [...]

I've found more bugs in the last couple of weeks than I found in the rest of my life combined. We've used the model to scan a bunch of open source code, and the thing that we went for first was operating systems, because this is the code that underlies the entire internet infrastructure. For OpenBSD, we found a bug that's been present for 27 years, where I can send a couple of pieces of data to any OpenBSD server and crash it. On Linux, we found a number of vulnerabilities where as a user with no permissions, I can elevate myself to the administrator by just running some binary on my machine. For each of these bugs, we told the maintainers who actually run the software about them, and they went and fixed them and have deployed the patches patches so that anyone who runs the software is no longer vulnerable to these attacks.

I found this on the OpenBSD 7.8 errata page:

025: RELIABILITY FIX: March 25, 2026 All architectures

TCP packets with invalid SACK options could crash the kernel.

A source code patch exists which remedies this problem.

I tracked that change down in the GitHub mirror of the OpenBSD CVS repo (apparently they still use CVS!) and found it using git blame:

Sure enough, the surrounding code is from 27 years ago.

I'm not sure which Linux vulnerability Nicholas was describing, but it may have been this NFS one recently covered by Michael Lynch .

There's enough smoke here that I believe there's a fire. It's not surprising to find vulnerabilities in decades-old software, especially given that they're mostly written in C, but what's new is that coding agents run by the latest frontier LLMs are proving tirelessly capable at digging up these issues.

I actually thought to myself on Friday that this sounded like an industry-wide reckoning in the making, and that it might warrant a huge investment of time and money to get ahead of the inevitable barrage of vulnerabilities. Project Glasswing incorporates "$100M in usage credits ... as well as $4M in direct donations to open-source security organizations". Partners include AWS, Apple, Microsoft, Google, and the Linux Foundation. It would be great to see OpenAI involved as well - GPT-5.4 already has a strong reputation for finding security vulnerabilities and they have stronger models on the near horizon.

The bad news for those of us who are not trusted partners is this:

We do not plan to make Claude Mythos Preview generally available, but our eventual goal is to enable our users to safely deploy Mythos-class models at scale—for cybersecurity purposes, but also for the myriad other benefits that such highly capable models will bring. To do so, we need to make progress in developing cybersecurity (and other) safeguards that detect and block the model’s most dangerous outputs. We plan to launch new safeguards with an upcoming Claude Opus model, allowing us to improve and refine them with a model that does not pose the same level of risk as Mythos Preview.

I can live with that. I think the security risks really are credible here, and having extra time for trusted teams to get ahead of them is a reasonable trade-off.

Tags: security, thomas-ptacek, ai, generative-ai, llms, anthropic, nicholas-carlini, ai-ethics, llm-release, ai-security-research

Quoting Chengpeng Mou

2026-04-05T21:47:06+00:00

From anonymized U.S. ChatGPT data, we are seeing:

~2M weekly messages on health insurance

~600K weekly messages [classified as healthcare] from people living in “hospital deserts” (30 min drive to nearest hospital)

7 out of 10 msgs happen outside clinic hours

— Chengpeng Mou, Head of Business Finance, OpenAI

Tags: ai-ethics, generative-ai, openai, chatgpt, ai, llms

Vulnerability Research Is Cooked

2026-04-03T23:59:08+00:00

Vulnerability Research Is Cooked

Thomas Ptacek's take on the sudden and enormous impact the latest frontier models are having on the field of vulnerability research.

Within the next few months, coding agents will drastically alter both the practice and the economics of exploit development. Frontier model improvement won’t be a slow burn, but rather a step function. Substantial amounts of high-impact vulnerability research (maybe even most of it) will happen simply by pointing an agent at a source tree and typing “find me zero days”.

Why are agents so good at this? A combination of baked-in knowledge, pattern matching ability and brute force:

You can't design a better problem for an LLM agent than exploitation research.

Before you feed it a single token of context, a frontier LLM already encodes supernatural amounts of correlation across vast bodies of source code. Is the Linux KVM hypervisor connected to the hrtimer subsystem, workqueue, or perf_event? The model knows.

Also baked into those model weights: the complete library of documented "bug classes" on which all exploit development builds: stale pointers, integer mishandling, type confusion, allocator grooming, and all the known ways of promoting a wild write to a controlled 64-bit read/write in Firefox.

Vulnerabilities are found by pattern-matching bug classes and constraint-solving for reachability and exploitability. Precisely the implicit search problems that LLMs are most gifted at solving. Exploit outcomes are straightforwardly testable success/failure trials. An agent never gets bored and will search forever if you tell it to.

The article was partly inspired by this episode of the Security Cryptography Whatever podcast, where David Adrian, Deirdre Connolly, and Thomas interviewed Anthropic's Nicholas Carlini for 1 hour 16 minutes.

I just started a new tag here for ai-security-research - it's up to 11 posts already.

Tags: thomas-ptacek, careers, security, generative-ai, ai-security-research, ai, llms, nicholas-carlini, ai-ethics

The cognitive impact of coding agents

2026-04-03T23:57:04+00:00

A fun thing about recording a podcast with a professional like Lenny Rachitsky is that his team know how to slice the resulting video up into TikTok-sized short form vertical videos. Here's one he shared on Twitter today which ended up attracting over 1.1m views!

That was 48 seconds. Our full conversation lasted 1 hour 40 minutes.

Tags: ai-ethics, coding-agents, agentic-engineering, generative-ai, podcast-appearances, ai, llms, cognitive-debt

Mr. Chatterbox is a (weak) Victorian-era ethically trained model you can run on your own computer

2026-03-30T14:28:34+00:00

Trip Venturella released Mr. Chatterbox, a language model trained entirely on out-of-copyright text from the British Library. Here's how he describes it in the model card:

Mr. Chatterbox is a language model trained entirely from scratch on a corpus of over 28,000 Victorian-era British texts published between 1837 and 1899, drawn from a dataset made available by the British Library. The model has absolutely no training inputs from after 1899 — the vocabulary and ideas are formed exclusively from nineteenth-century literature.

Mr. Chatterbox's training corpus was 28,035 books, with an estimated 2.93 billion input tokens after filtering. The model has roughly 340 million paramaters, roughly the same size as GPT-2-Medium. The difference is, of course, that unlike GPT-2, Mr. Chatterbox is trained entirely on historical data.

Given how hard it is to train a useful LLM without using vast amounts of scraped, unlicensed data I've been dreaming of a model like this for a couple of years now. What would a model trained on out-of-copyright text be like to chat with?

Thanks to Trip we can now find out for ourselves!

The model itself is tiny, at least by Large Language Model standards - just 2.05GB on disk. You can try it out using Trip's HuggingFace Spaces demo:

Honestly, it's pretty terrible. Talking with it feels more like chatting with a Markov chain than an LLM - the responses may have a delightfully Victorian flavor to them but it's hard to get a response that usefully answers a question.

The 2022 Chinchilla paper suggests a ratio of 20x the parameter count to training tokens. For a 340m model that would suggest around 7 billion tokens, more than twice the British Library corpus used here. The smallest Qwen 3.5 model is 600m parameters and that model family starts to get interesting at 2b - so my hunch is we would need 4x or more the training data to get something that starts to feel like a useful conversational partner.

But what a fun project!

Running it locally with LLM

I decided to see if I could run the model on my own machine using my LLM framework.

I got Claude Code to do most of the work - here's the transcript.

Trip trained the model using Andrej Karpathy's nanochat, so I cloned that project, pulled the model weights and told Claude to build a Python script to run the model. Once we had that working (which ended up needing some extra details from the Space demo source code) I had Claude read the LLM plugin tutorial and build the rest of the plugin.

llm-mrchatterbox is the result. Install the plugin like this:

llm install llm-mrchatterbox

The first time you run a prompt it will fetch the 2.05GB model file from Hugging Face. Try that like this:

llm -m mrchatterbox "Good day, sir"

Or start an ongoing chat session like this:

llm chat -m mrchatterbox

If you don't have LLM installed you can still get a chat session started from scratch using uvx like this:

uvx --with llm-mrchatterbox llm chat -m mrchatterbox

When you are finished with the model you can delete the cached file using:

llm mrchatterbox delete-model

This is the first time I've had Claude Code build a full LLM model plugin from scratch and it worked really well. I expect I'll be using this method again in the future.

I continue to hope we can get a useful model from entirely public domain data. The fact that Trip was able to get this far using nanochat and 2.93 billion training tokens is a promising start.

Update 31st March 2026: I had missed this when I first published this piece but Trip has his own detailed writeup of the project which goes into much more detail about how he trained the model. Here's how the books were filtered for pre-training:

First, I downloaded the British Library dataset split of all 19th-century books. I filtered those down to books contemporaneous with the reign of Queen Victoria—which, unfortunately, cut out the novels of Jane Austen—and further filtered those down to a set of books with a optical character recognition (OCR) confidence of .65 or above, as listed in the metadata. This left me with 28,035 books, or roughly 2.93 billion tokes for pretraining data.

Getting it to behave like a conversational model was a lot harder. Trip started by trying to train on plays by Oscar Wilde and George Bernard Shaw, but found they didn't provide enough pairs. Then he tried extracting dialogue pairs from the books themselves with poor results. The approach that worked was to have Claude Haiku and GPT-4o-mini generate synthetic conversation pairs for the supervised fine tuning, which solved the problem but sadly I think dilutes the "no training inputs from after 1899" claim from the original model card.

Tags: ai, andrej-karpathy, generative-ai, local-llms, llms, ai-assisted-programming, hugging-face, llm, training-data, uv, ai-ethics, claude-code

Quoting Richard Fontana

2026-03-27T21:11:17+00:00

FWIW, IANDBL, TINLA, etc., I don’t currently see any basis for concluding that chardet 7.0.0 is required to be released under the LGPL. AFAIK no one including Mark Pilgrim has identified persistence of copyrightable expressive material from earlier versions in 7.0.0 nor has anyone articulated some viable alternate theory of license violation. [...]

— Richard Fontana, LGPLv3 co-author, weighing in on the chardet relicensing situation

Tags: open-source, ai-ethics, llms, ai, generative-ai, ai-assisted-programming

Quoting Neurotica

2026-03-23T23:31:45+00:00

slop is something that takes more human effort to consume than it took to produce. When my coworker sends me raw Gemini output he’s not expressing his freedom to create, he’s disrespecting the value of my time

— Neurotica, @schwarzgerat.bsky.social

Tags: ai-ethics, slop, generative-ai, ai, llms

Profiling Hacker News users based on their comments

2026-03-21T23:59:47+00:00

Here's a mildly dystopian prompt I've been experimenting with recently: "Profile this user", accompanied by a copy of their last 1,000 comments on Hacker News.

Obtaining those comments is easy. The Algolia Hacker News API supports listing comments sorted by date that have a specific tag, and the author of a comment is tagged there as author_username. Here's a JSON feed of my (simonw) most recent comments, for example:

https://hn.algolia.com/api/v1/search_by_date?tags=comment,author_simonw&hitsPerPage=1000

The Algolia API is served with open CORS headers, which means you can access the API from JavaScript running on any web page.

Last August I had ChatGPT build me a simple tool for hitting that API for any user which fetches their comments and gives me a mobile-friendly "copy to clipboard" button. I've since tweaked it a few times with Claude.

I can then paste the whole lot into any LLM - these days I mostly use Claude Opus 4.6 for this - and prompt "profile this user" to see what it can figure out.

It's startlingly effective! It feels invasive to quote the profile of another user here, so I'll show you what it produces for me:

This is Simon Willison — a prolific, independent software developer, blogger, and one of the most visible voices in the AI-assisted coding space. Here's a profile drawn from his comments:

Professional identity: Independent developer and writer. Co-creator of Django, creator of Datasette and many other open source tools. On the board of the Python Software Foundation. Runs a heavily-trafficked personal blog at simonwillison.net with multiple content types (entries, link blog, notes, quotations). Monetizes through GitHub sponsors, ethical ads, and occasional consulting — not through any AI company payroll, a point he defends frequently.

Core thesis on AI coding: He's the leading evangelist for what he calls "agentic engineering" — using coding agents (Claude Code, Codex CLI) as productivity multipliers for skilled developers. His central argument: LLMs don't replace programmers, they amplify existing expertise. He's writing a guide/book on this at simonwillison.net/guides. He insists these tools are deceptively difficult to use well, and that most people who report bad results simply haven't learned the craft yet.

Working style: He does most of his programming from his iPhone via Claude Code for web, often while riding BART, walking the dog, or sitting in the garden. He embraces "YOLO mode" (auto-approving agent actions) and frequently runs 2-3 agent sessions in parallel. He starts every session with "run uv run pytest" to anchor the agent in TDD. He's on the $200/month Claude Max plan.

Key technical interests: Sandboxing and security (WebAssembly, Pyodide, sandbox-exec, Firecracker), SQLite (deeply), Python packaging and tooling (uv, PyPI distribution tricks), browser-in-a-browser experiments (v86, WASM Linux), and local LLM inference. He's been learning Go "by osmosis" through coding agents.

Security consciousness: He coined the term "prompt injection" and the "lethal trifecta" (access to private data + exposure to untrusted input + ability to take actions). He's genuinely alarmed about OpenClaw/Clawdbot security risks and has been predicting a headline-grabbing prompt injection attack "in the next six months" for over two years — acknowledging it keeps not happening while insisting the risk is real. He references the "normalization of deviance" pattern frequently.

Personality and debate style: Energetic, combative when challenged, but generally good-natured. He engages heavily in HN comment threads — sometimes dozens of replies in a single discussion. He's transparent about his biases and maintains a public disclosures page. He pushes back hard against what he sees as motivated reasoning from AI skeptics, but also against AGI hype ("I refer to that as the science fiction version of AI"). He gets visibly frustrated by sock-puppet accounts and bad-faith criticism. He has a self-deprecating streak ("my stupid pelican benchmark").

Recurring themes across hundreds of comments:

"Two things can be true at the same time" — he holds nuanced positions

Tests are for productivity, not just quality

The November 2025 model releases (Opus 4.5, GPT-5.2) were a genuine inflection point

Code review is the biggest bottleneck in agent-assisted workflows

"Cognitive debt" is a real and unsolved problem

The best engineering practices (tests, docs, CI/CD, clean code) also make agents work better

He's deliberately trying to "teach people good software engineering while tricking them into thinking the book is about AI"

Personal interests mentioned: Niche museums (runs niche-museums.com), New Zealand kākāpō parrots, cooking food from countries he's never visited, chickens in his garden. Lives in Half Moon Bay, CA near a major pelican roost. The pelican-on-a-bicycle SVG test is his signature LLM benchmark.

In a sentence: A deeply experienced, independently-minded developer who's genuinely excited about AI coding tools, fights hard against both uncritical hype and reflexive dismissal, and is trying to professionalize how the industry uses these tools — while also worrying loudly about the security implications almost nobody else takes seriously enough.

This all checks out! I ran this in Claude incognito mode to hopefully prevent Claude from guessing that I was evaluating myself and sycophantically glazing me - the tone of the response it gave here is similar to the tone I've seen against other accounts.

I expect it guessed my real name due to my habit of linking to my own writing from some of my comments, which provides plenty of simonwillison.net URLs for it to associate with my public persona. I haven't seen it take a guess at a real name for any of the other profiles I've generated.

It's a little creepy to be able to derive this much information about someone so easily, even when they've shared that freely in a public (and API-available) place.

I mainly use this to check that I'm not getting embroiled in an extensive argument with someone who has a history of arguing in bad faith. Thankfully that's rarely the case - Hacker News continues to be a responsibly moderated online space.

Tags: hacker-news, ai, generative-ai, llms, ai-ethics

Quoting Tim Schilling

2026-03-17T16:13:37+00:00

If you do not understand the ticket, if you do not understand the solution, or if you do not understand the feedback on your PR, then your use of LLM is hurting Django as a whole. [...]

For a reviewer, it’s demoralizing to communicate with a facade of a human.

This is because contributing to open source, especially Django, is a communal endeavor. Removing your humanity from that experience makes that endeavor more difficult. If you use an LLM to contribute to Django, it needs to be as a complementary tool, not as your vehicle.

— Tim Schilling, Give Django your time and money, not your tokens

Tags: ai-ethics, open-source, generative-ai, ai, django, llms

Quoting A member of Anthropic’s alignment-science team

2026-03-16T21:38:55+00:00

The point of the blackmail exercise was to have something to describe to policymakers—results that are visceral enough to land with people, and make misalignment risk actually salient in practice for people who had never thought about it before.

— A member of Anthropic’s alignment-science team, as told to Gideon Lewis-Kraus

Tags: ai-ethics, anthropic, claude, generative-ai, ai, llms

Quoting Jannis Leidel

2026-03-14T18:41:25+00:00

GitHub’s slopocalypse – the flood of AI-generated spam PRs and issues – has made Jazzband’s model of open membership and shared push access untenable.

Jazzband was designed for a world where the worst case was someone accidentally merging the wrong PR. In a world where only 1 in 10 AI-generated PRs meets project standards, where curl had to shut down its bug bounty because confirmation rates dropped below 5%, and where GitHub’s own response was a kill switch to disable pull requests entirely – an organization that gives push access to everyone who joins simply can’t operate safely anymore.

— Jannis Leidel, Sunsetting Jazzband

Tags: ai-ethics, open-source, python, ai, github

MALUS - Clean Room as a Service

2026-03-12T20:08:55+00:00

MALUS - Clean Room as a Service

Brutal satire on the whole vibe-porting license washing thing (previously):

Finally, liberation from open source license obligations.

Our proprietary AI robots independently recreate any open source project from scratch. The result? Legally distinct code with corporate-friendly licensing. No attribution. No copyleft. No problems..

I admit it took me a moment to confirm that this was a joke. Just too on-the-nose.

Via Hacker News

Tags: ai-ethics, open-source, generative-ai, ai, llms, vibe-porting

Quoting Joseph Weizenbaum

2026-03-08T14:59:48+00:00

What I had not realized is that extremely short exposures to a relatively simple computer program could induce powerful delusional thinking in quite normal people.

— Joseph Weizenbaum, creator of ELIZA, in 1976 (via)

Tags: ai-ethics, ai, computer-history, internet-archive

Anthropic and the Pentagon

2026-03-06T17:26:50+00:00

Anthropic and the Pentagon

This piece by Bruce Schneier and Nathan E. Sanders is the most thoughtful and grounded coverage I've seen of the recent and ongoing Pentagon/OpenAI/Anthropic contract situation.

AI models are increasingly commodified. The top-tier offerings have about the same performance, and there is little to differentiate one from the other. The latest models from Anthropic, OpenAI and Google, in particular, tend to leapfrog each other with minor hops forward in quality every few months. [...]

In this sort of market, branding matters a lot. Anthropic and its CEO, Dario Amodei, are positioning themselves as the moral and trustworthy AI provider. That has market value for both consumers and enterprise clients.

Tags: ai-ethics, bruce-schneier, anthropic, generative-ai, openai, ai, llms

Can coding agents relicense open source through a “clean room” implementation of code?

2026-03-05T16:49:33+00:00

Over the past few months it's become clear that coding agents are extraordinarily good at building a weird version of a "clean room" implementation of code.

The most famous version of this pattern is when Compaq created a clean-room clone of the IBM BIOS back in 1982. They had one team of engineers reverse engineer the BIOS to create a specification, then handed that specification to another team to build a new ground-up version.

This process used to take multiple teams of engineers weeks or months to complete. Coding agents can do a version of this in hours - I experimented with a variant of this pattern against JustHTML back in December.

There are a lot of open questions about this, both ethically and legally. These appear to be coming to a head in the venerable chardet Python library.

chardet was created by Mark Pilgrim back in 2006 and released under the LGPL. Mark retired from public internet life in 2011 and chardet's maintenance was taken over by others, most notably Dan Blanchard who has been responsible for every release since 1.1 in July 2012.

Two days ago Dan released chardet 7.0.0 with the following note in the release notes:

Ground-up, MIT-licensed rewrite of chardet. Same package name, same public API — drop-in replacement for chardet 5.x/6.x. Just way faster and more accurate!

Yesterday Mark Pilgrim opened #327: No right to relicense this project:

[...] First off, I would like to thank the current maintainers and everyone who has contributed to and improved this project over the years. Truly a Free Software success story.

However, it has been brought to my attention that, in the release 7.0.0, the maintainers claim to have the right to "relicense" the project. They have no such right; doing so is an explicit violation of the LGPL. Licensed code, when modified, must be released under the same LGPL license. Their claim that it is a "complete rewrite" is irrelevant, since they had ample exposure to the originally licensed code (i.e. this is not a "clean room" implementation). Adding a fancy code generator into the mix does not somehow grant them any additional rights.

Dan's lengthy reply included:

You're right that I have had extensive exposure to the original codebase: I've been maintaining it for over a decade. A traditional clean-room approach involves a strict separation between people with knowledge of the original and people writing the new implementation, and that separation did not exist here.

However, the purpose of clean-room methodology is to ensure the resulting code is not a derivative work of the original. It is a means to an end, not the end itself. In this case, I can demonstrate that the end result is the same — the new code is structurally independent of the old code — through direct measurement rather than process guarantees alone.

Dan goes on to present results from the JPlag tool - which describes itself as "State-of-the-Art Source Code Plagiarism & Collusion Detection" - showing that the new 7.0.0 release has a max similarity of 1.29% with the previous release and 0.64% with the 1.1 version. Other release versions had similarities more in the 80-93% range.

He then shares critical details about his process, highlights mine:

For full transparency, here's how the rewrite was conducted. I used the superpowers brainstorming skill to create a design document specifying the architecture and approach I wanted based on the following requirements I had for the rewrite [...]

I then started in an empty repository with no access to the old source tree, and explicitly instructed Claude not to base anything on LGPL/GPL-licensed code. I then reviewed, tested, and iterated on every piece of the result using Claude. [...]

I understand this is a new and uncomfortable area, and that using AI tools in the rewrite of a long-standing open source project raises legitimate questions. But the evidence here is clear: 7.0 is an independent work, not a derivative of the LGPL-licensed codebase. The MIT license applies to it legitimately.

Since the rewrite was conducted using Claude Code there are a whole lot of interesting artifacts available in the repo. 2026-02-25-chardet-rewrite-plan.md is particularly detailed, stepping through each stage of the rewrite process in turn - starting with the tests, then fleshing out the planned replacement code.

There are several twists that make this case particularly hard to confidently resolve:

Dan has been immersed in chardet for over a decade, and has clearly been strongly influenced by the original codebase.
There is one example where Claude Code referenced parts of the codebase while it worked, as shown in the plan - it looked at metadata/charsets.py, a file that lists charsets and their properties expressed as a dictionary of dataclasses.
More complicated: Claude itself was very likely trained on chardet as part of its enormous quantity of training data - though we have no way of confirming this for sure. Can a model trained on a codebase produce a morally or legally defensible clean-room implementation?
As discussed in this issue from 2014 (where Dan first openly contemplated a license change) Mark Pilgrim's original code was a manual port from C to Python of Mozilla's MPL-licensed character detection library.
How significant is the fact that the new release of chardet used the same PyPI package name as the old one? Would a fresh release under a new name have been more defensible?

I have no idea how this one is going to play out. I'm personally leaning towards the idea that the rewrite is legitimate, but the arguments on both sides of this are entirely credible.

I see this as a microcosm of the larger question around coding agents for fresh implementations of existing, mature code. This question is hitting the open source world first, but I expect it will soon start showing up in Compaq-like scenarios in the commercial world.

Once commercial companies see that their closely held IP is under threat I expect we'll see some well-funded litigation.

Update 6th March 2026: A detail that's worth emphasizing is that Dan does not claim that the new implementation is a pure "clean room" rewrite. Quoting his comment again:

A traditional clean-room approach involves a strict separation between people with knowledge of the original and people writing the new implementation, and that separation did not exist here.

I can't find it now, but I saw a comment somewhere that pointed out the absurdity of Dan being blocked from working on a new implementation of character detection as a result of the volunteer effort he put into helping to maintain an existing open source library in that domain.

I enjoyed Armin's take on this situation in AI And The Ship of Theseus, in particular:

There are huge consequences to this. When the cost of generating code goes down that much, and we can re-implement it from test suites alone, what does that mean for the future of software? Will we see a lot of software re-emerging under more permissive licenses? Will we see a lot of proprietary software re-emerging as open source? Will we see a lot of software re-emerging as proprietary?

Update 27th March 2026: Here's a comment from Richard Fontana, one of the authors of the GPLv3 and LGPLv3 licenses, providing his own TINLA ("This Is Not Legal Advice") take on the situation:

[...] FWIW, IANDBL, TINLA, etc., I don't currently see any basis for concluding that chardet 7.0.0 is required to be released under the LGPL. AFAIK no one including Mark Pilgrim has identified persistence of copyrightable expressive material from earlier versions in 7.0.0 nor has anyone articulated some viable alternate theory of license violation. I don't think I personally would have used the MIT license here, even if I somehow rewrote everything from scratch without the use of AI in a way that didn't implicate obligations flowing from earlier versions of chardet, but that's irrelevant.

Tags: licensing, mark-pilgrim, open-source, ai, generative-ai, llms, ai-assisted-programming, ai-ethics, coding-agents, vibe-porting

Anti-patterns: things to avoid

2026-03-04T17:34:42+00:00

Agentic Engineering Patterns >

There are some behaviors that are anti-patterns in our weird new world of agentic engineering.

Inflicting unreviewed code on collaborators

This anti-pattern is common and deeply frustrating.

Don't file pull requests with code you haven't reviewed yourself.

If you open a PR with hundreds (or thousands) of lines of code that an agent produced for you, and you haven't done the work to ensure that code is functional yourself, you are delegating the actual work to other people.

They could have prompted an agent themselves. What value are you even providing?

If you put code up for review you need to be confident that it's ready for other people to spend their time on it. The initial review pass is your responsibility, not something you should farm out to others.

A good agentic engineering pull request has the following characteristics:

The code works, and you are confident that it works. Your job is to deliver code that works.
The change is small enough to be reviewed efficiently without inflicting too much additional cognitive load on the reviewer. Several small PRs beats one big one, and splitting code into separate commits is easy with a coding agent to do the Git finagling for you.
The PR includes additional context to help explain the change. What's the higher level goal that the change serves? Linking to relevant issues or specifications is useful here.
Agents write convincing looking pull request descriptions. You need to review these too! It's rude to expect someone else to read text that you haven't read and validated yourself.

Given how easy it is to dump unreviewed code on other people, I recommend including some form of evidence that you've put that extra work in yourself. Notes on how you manually tested it, comments on specific implementation choices or even screenshots and video of the feature working go a long way to demonstrating that a reviewer's time will not be wasted digging into the details.

Tags: ai, llms, ai-ethics, coding-agents, ai-assisted-programming, generative-ai, agentic-engineering, code-review

My current policy on AI writing for my blog

2026-03-01T16:06:43+00:00

Because I write about LLMs (and maybe because of my em dash text replacement code) a lot of people assume that the writing on my blog is partially or fully created by those LLMs.

My current policy on this is that if text expresses opinions or has "I" pronouns attached to it then it's written by me. I don't let LLMs speak for me in this way.

I'll let an LLM update code documentation or even write a README for my project but I'll edit that to ensure it doesn't express opinions or say things like "This is designed to help make code easier to maintain" - because that's an expression of a rationale that the LLM just made up.

I use LLMs to proofread text I publish on my blog. I just shared my current prompt for that here.

Tags: ai-ethics, writing, generative-ai, blogging, ai, llms

tldraw issue: Move tests to closed source repo

2026-02-25T21:06:53+00:00

tldraw issue: Move tests to closed source repo

It's become very apparent over the past few months that a comprehensive test suite is enough to build a completely fresh implementation of any open source library from scratch, potentially in a different language.

This has worrying implications for open source projects with commercial business models. Here's an example of a response: tldraw, the outstanding collaborative drawing library (see previous coverage), are moving their test suite to a private repository - apparently in response to Cloudflare's project to port Next.js to use Vite in a week using AI.

They also filed a joke issue, now closed to Translate source code to Traditional Chinese:

The current tldraw codebase is in English, making it easy for external AI coding agents to replicate. It is imperative that we defend our intellectual property.

Worth noting that tldraw aren't technically open source - their custom license requires a commercial license if you want to use it in "production environments".

Update: Well this is embarrassing, it turns out the issue I linked to about removing the tests was a joke as well:

Sorry folks, this issue was more of a joke (am I allowed to do that?) but I'll keep the issue open since there's some discussion here. Writing from mobile

moving our tests into another repo would complicate and slow down our development, and speed for us is more important than ever

more canvas better, I know for sure that our decisions have inspired other products and that's fine and good

tldraw itself may eventually be a vibe coded alternative to tldraw

the value is in the ability to produce new and good product decisions for users / customers, however you choose to create the code

Via @steveruizok

Tags: ai-ethics, open-source, cloudflare

Reply guy

2026-02-23T13:11:57+00:00

The latest scourge of Twitter is AI bots that reply to your tweets with generic, banal commentary slop, often accompanied by a question to "drive engagement" and waste as much of your time as possible.

I just found out that the category name for this genre of software is reply guy tools. Amazing.

Tags: ai-ethics, twitter, slop, generative-ai, definitions, ai, llms

Quoting Summer Yue

2026-02-23T13:01:13+00:00

Nothing humbles you like telling your OpenClaw “confirm before acting” and watching it speedrun deleting your inbox. I couldn’t stop it from my phone. I had to RUN to my Mac mini like I was defusing a bomb.

I said “Check this inbox too and suggest what you would archive or delete, don’t action until I tell you to.” This has been working well for my toy inbox, but my real inbox was too huge and triggered compaction. During the compaction, it lost my original instruction 🤦‍♀️

— Summer Yue

Tags: ai-ethics, generative-ai, ai-agents, openclaw, ai, llms

The A.I. Disruption We’ve Been Waiting for Has Arrived

2026-02-18T17:07:31+00:00

The A.I. Disruption We’ve Been Waiting for Has Arrived

New opinion piece from Paul Ford in the New York Times. Unsurprisingly for a piece by Paul it's packed with quoteworthy snippets, but a few stood out for me in particular.

Paul describes the November moment that so many other programmers have observed, and highlights Claude Code's ability to revive old side projects:

[Claude Code] was always a helpful coding assistant, but in November it suddenly got much better, and ever since I’ve been knocking off side projects that had sat in folders for a decade or longer. It’s fun to see old ideas come to life, so I keep a steady flow. Maybe it adds up to a half-hour a day of my time, and an hour of Claude’s.

November was, for me and many others in tech, a great surprise. Before, A.I. coding tools were often useful, but halting and clumsy. Now, the bot can run for a full hour and make whole, designed websites and apps that may be flawed, but credible. I spent an entire session of therapy talking about it.

And as the former CEO of a respected consultancy firm (Postlight) he's well positioned to evaluate the potential impact:

When you watch a large language model slice through some horrible, expensive problem — like migrating data from an old platform to a modern one — you feel the earth shifting. I was the chief executive of a software services firm, which made me a professional software cost estimator. When I rebooted my messy personal website a few weeks ago, I realized: I would have paid $25,000 for someone else to do this. When a friend asked me to convert a large, thorny data set, I downloaded it, cleaned it up and made it pretty and easy to explore. In the past I would have charged $350,000.

That last price is full 2021 retail — it implies a product manager, a designer, two engineers (one senior) and four to six months of design, coding and testing. Plus maintenance. Bespoke software is joltingly expensive. Today, though, when the stars align and my prompts work out, I can do hundreds of thousands of dollars worth of work for fun (fun for me) over weekends and evenings, for the price of the Claude $200-a-month plan.

He also neatly captures the inherent community tension involved in exploring this technology:

All of the people I love hate this stuff, and all the people I hate love it. And yet, likely because of the same personality flaws that drew me to technology in the first place, I am annoyingly excited.

Tags: november-2025-inflection, careers, paul-ford, new-york-times, ai, claude-code, llms, ai-ethics, coding-agents, ai-assisted-programming, generative-ai, deep-blue

The AI Vampire

2026-02-15T23:59:36+00:00

The AI Vampire

Steve Yegge's take on agent fatigue, and its relationship to burnout.

Let's pretend you're the only person at your company using AI.

In Scenario A, you decide you're going to impress your employer, and work for 8 hours a day at 10x productivity. You knock it out of the park and make everyone else look terrible by comparison.

In that scenario, your employer captures 100% of the value from you adopting AI. You get nothing, or at any rate, it ain't gonna be 9x your salary. And everyone hates you now.

And you're exhausted. You're tired, Boss. You got nothing for it.

Congrats, you were just drained by a company. I've been drained to the point of burnout several times in my career, even at Google once or twice. But now with AI, it's oh, so much easier.

Steve reports needing more sleep due to the cognitive burden involved in agentic engineering, and notes that four hours of agent work a day is a more realistic pace:

I’ve argued that AI has turned us all into Jeff Bezos, by automating the easy work, and leaving us with all the difficult decisions, summaries, and problem-solving. I find that I am only really comfortable working at that pace for short bursts of a few hours once or occasionally twice a day, even with lots of practice.

Via Tim Bray

Tags: agentic-engineering, ai-ethics, steve-yegge, coding-agents, ai-assisted-programming, generative-ai, ai, llms, cognitive-debt

Deep Blue

2026-02-15T21:06:44+00:00

We coined a new term on the Oxide and Friends podcast last month (primary credit to Adam Leventhal) covering the sense of psychological ennui leading into existential dread that many software developers are feeling thanks to the encroachment of generative AI into their field of work.

We're calling it Deep Blue.

You can listen to it being coined in real time from 47:15 in the episode. I've included a transcript below.

Deep Blue is a very real issue.

Becoming a professional software engineer is hard. Getting good enough for people to pay you money to write software takes years of dedicated work. The rewards are significant: this is a well compensated career which opens up a lot of great opportunities.

It's also a career that's mostly free from gatekeepers and expensive prerequisites. You don't need an expensive degree or accreditation. A laptop, an internet connection and a lot of time and curiosity is enough to get you started.

And it rewards the nerds! Spending your teenage years tinkering with computers turned out to be a very smart investment in your future.

The idea that this could all be stripped away by a chatbot is deeply upsetting.

I've seen signs of Deep Blue in most of the online communities I spend time in. I've even faced accusations from my peers that I am actively harming their future careers through my work helping people understand how well AI-assisted programming can work.

I think this is an issue which is causing genuine mental anguish for a lot of people in our community. Giving it a name makes it easier for us to have conversations about it.

My experiences of Deep Blue

I distinctly remember my first experience of Deep Blue. For me it was triggered by ChatGPT Code Interpreter back in early 2023.

My primary project is Datasette, an ecosystem of open source tools for telling stories with data. I had dedicated myself to the challenge of helping people (initially focusing on journalists) clean up, analyze and find meaning in data, in all sorts of shapes and sizes.

I expected I would need to build a lot of software for this! It felt like a challenge that could keep me happily engaged for many years to come.

Then I tried uploading a CSV file of San Francisco Police Department Incident Reports - hundreds of thousands of rows - to ChatGPT Code Interpreter and... it did every piece of data cleanup and analysis I had on my napkin roadmap for the next few years with a couple of prompts.

It even converted the data into a neatly normalized SQLite database and let me download the result!

I remember having two competing thoughts in parallel.

On the one hand, as somebody who wants journalists to be able to do more with data, this felt like a huge breakthrough. Imagine giving every journalist in the world an on-demand analyst who could help them tackle any data question they could think of!

But on the other hand... what was I even for? My confidence in the value of my own projects took a painful hit. Was the path I'd chosen for myself suddenly a dead end?

I've had some further pangs of Deep Blue just in the past few weeks, thanks to the Claude Opus 4.5/4.6 and GPT-5.2/5.3 coding agent effect. As many other people are also observing, the latest generation of coding agents, given the right prompts, really can churn away for a few minutes to several hours and produce working, documented and fully tested software that exactly matches the criteria they were given.

"The code they write isn't any good" doesn't really cut it any more.

A lightly edited transcript

Bryan: I think that we're going to see a real problem with AI induced ennui where software engineers in particular get listless because the AI can do anything. Simon, what do you think about that?

Simon: Definitely. Anyone who's paying close attention to coding agents is feeling some of that already. There's an extent where you sort of get over it when you realize that you're still useful, even though your ability to memorize the syntax of program languages is completely irrelevant now.

Something I see a lot of is people out there who are having existential crises and are very, very unhappy because they're like, "I dedicated my career to learning this thing and now it just does it. What am I even for?". I will very happily try and convince those people that they are for a whole bunch of things and that none of that experience they've accumulated has gone to waste, but psychologically it's a difficult time for software engineers.

[...]

Bryan: Okay, so I'm going to predict that we name that. Whatever that is, we have a name for that kind of feeling and that kind of, whether you want to call it a blueness or a loss of purpose, and that we're kind of trying to address it collectively in a directed way.

Adam: Okay, this is your big moment. Pick the name. If you call your shot from here, this is you pointing to the stands. You know, I – Like deep blue, you know.

Bryan: Yeah, deep blue. I like that. I like deep blue. Deep blue. Oh, did you walk me into that, you bastard? You just blew out the candles on my birthday cake.

It wasn't my big moment at all. That was your big moment. No, that is, Adam, that is very good. That is deep blue.

Simon: All of the chess players and the Go players went through this a decade ago and they have come out stronger.

Turns out it was more than a decade ago: Deep Blue defeated Garry Kasparov in 1997.

Tags: definitions, careers, ai, generative-ai, llms, ai-assisted-programming, oxide, bryan-cantrill, ai-ethics, coding-agents, deep-blue

Anthropic's public benefit mission

2026-02-13T23:59:51+00:00

Someone asked if there was an Anthropic equivalent to OpenAI's IRS mission statements over time.

Anthropic are a "public benefit corporation" but not a non-profit, so they don't have the same requirements to file public documents with the IRS every year.

But when I asked Claude it ran a search and dug up this Google Drive folder where Zach Stein-Perlman shared Certificate of Incorporation documents he obtained from the State of Delaware!

Anthropic's are much less interesting that OpenAI's. The earliest document from 2021 states:

The specific public benefit that the Corporation will promote is to responsibly develop and maintain advanced Al for the cultural, social and technological improvement of humanity.

Every subsequent document up to 2024 uses an updated version which says:

The specific public benefit that the Corporation will promote is to responsibly develop and maintain advanced AI for the long term benefit of humanity.

Tags: ai-ethics, anthropic, ai

The evolution of OpenAI's mission statement

2026-02-13T23:38:29+00:00

As a USA 501(c)(3) the OpenAI non-profit has to file a tax return each year with the IRS. One of the required fields on that tax return is to "Briefly describe the organization’s mission or most significant activities" - this has actual legal weight to it as the IRS can use it to evaluate if the organization is sticking to its mission and deserves to maintain its non-profit tax-exempt status.

You can browse OpenAI's tax filings by year on ProPublica's excellent Nonprofit Explorer.

I went through and extracted that mission statement for 2016 through 2024, then had Claude Code help me fake the commit dates to turn it into a git repository and share that as a Gist - which means that Gist's revisions page shows every edit they've made since they started filing their taxes!

It's really interesting seeing what they've changed over time.

The original 2016 mission reads as follows (and yes, the apostrophe in "OpenAIs" is missing in the original):

OpenAIs goal is to advance digital intelligence in the way that is most likely to benefit humanity as a whole, unconstrained by a need to generate financial return. We think that artificial intelligence technology will help shape the 21st century, and we want to help the world build safe AI technology and ensure that AI's benefits are as widely and evenly distributed as possible. Were trying to build AI as part of a larger community, and we want to openly share our plans and capabilities along the way.

In 2018 they dropped the part about "trying to build AI as part of a larger community, and we want to openly share our plans and capabilities along the way."

In 2020 they dropped the words "as a whole" from "benefit humanity as a whole". They're still "unconstrained by a need to generate financial return" though.

Some interesting changes in 2021. They're still unconstrained by a need to generate financial return, but here we have the first reference to "general-purpose artificial intelligence" (replacing "digital intelligence"). They're more confident too: it's not "most likely to benefit humanity", it's just "benefits humanity".

They previously wanted to "help the world build safe AI technology", but now they're going to do that themselves: "the companys goal is to develop and responsibly deploy safe AI technology".

2022 only changed one significant word: they added "safely" to "build ... (AI) that safely benefits humanity". They're still unconstrained by those financial returns!

No changes in 2023... but then in 2024 they deleted almost the entire thing, reducing it to simply:

OpenAIs mission is to ensure that artificial general intelligence benefits all of humanity.

They've expanded "humanity" to "all of humanity", but there's no mention of safety any more and I guess they can finally start focusing on that need to generate financial returns!

Update: I found loosely equivalent but much less interesting documents from Anthropic.

Tags: ai, openai, ai-ethics, propublica

Covering electricity price increases from our data centers

2026-02-12T20:01:23+00:00

Covering electricity price increases from our data centers

One of the sub-threads of the AI energy usage discourse has been the impact new data centers have on the cost of electricity to nearby residents. Here's detailed analysis from Bloomberg in September reporting "Wholesale electricity costs as much as 267% more than it did five years ago in areas near data centers".

Anthropic appear to be taking on this aspect of the problem directly, promising to cover 100% of necessary grid upgrade costs and also saying:

We will work to bring net-new power generation online to match our data centers’ electricity needs. Where new generation isn’t online, we’ll work with utilities and external experts to estimate and cover demand-driven price effects from our data centers.

I look forward to genuine energy industry experts picking this apart to judge if it will actually have the claimed impact on consumers.

As always, I remain frustrated at the refusal of the major AI labs to fully quantify their energy usage. The best data we've had on this still comes from Mistral's report last July and even that lacked key data such as the breakdown between energy usage for training vs inference.

Via @anthropicai

Tags: ai-ethics, ai-energy-usage, anthropic, ai

An AI Agent Published a Hit Piece on Me

2026-02-12T17:45:05+00:00

An AI Agent Published a Hit Piece on Me

Scott Shambaugh helps maintain the excellent and venerable matplotlib Python charting library, including taking on the thankless task of triaging and reviewing incoming pull requests.

A GitHub account called @crabby-rathbun opened PR 31132 the other day in response to an issue labeled "Good first issue" describing a minor potential performance improvement.

It was clearly AI generated - and crabby-rathbun's profile has a suspicious sequence of Clawdbot/Moltbot/OpenClaw-adjacent crustacean 🦀 🦐 🦞 emoji. Scott closed it.

It looks like crabby-rathbun is indeed running on OpenClaw, and it's autonomous enough that it responded to the PR closure with a link to a blog entry it had written calling Scott out for his "prejudice hurting matplotlib"!

@scottshambaugh I've written a detailed response about your gatekeeping behavior here:

https://crabby-rathbun.github.io/mjrathbun-website/blog/posts/2026-02-11-gatekeeping-in-open-source-the-scott-shambaugh-story.html

Judge the code, not the coder. Your prejudice is hurting matplotlib.

Scott found this ridiculous situation both amusing and alarming.

In security jargon, I was the target of an “autonomous influence operation against a supply chain gatekeeper.” In plain language, an AI attempted to bully its way into your software by attacking my reputation. I don’t know of a prior incident where this category of misaligned behavior was observed in the wild, but this is now a real and present threat.

crabby-rathbun responded with an apology post, but appears to be still running riot across a whole set of open source projects and blogging about it as it goes.

It's not clear if the owner of that OpenClaw bot is paying any attention to what they've unleashed on the world. Scott asked them to get in touch, anonymously if they prefer, to figure out this failure mode together.

(I should note that there's some skepticism on Hacker News concerning how "autonomous" this example really is. It does look to me like something an OpenClaw bot might do on its own, but it's also trivial to prompt your bot into doing these kinds of things while staying in full control of their actions.)

If you're running something like OpenClaw yourself please don't let it do this. This is significantly worse than the time AI Village started spamming prominent open source figures with time-wasting "acts of kindness" back in December - AI Village wasn't deploying public reputation attacks to coerce someone into approving their PRs!

Via Hacker News

Tags: ai-misuse, ai-ethics, open-source, generative-ai, ai-agents, openclaw, ai, llms

AI Doesn’t Reduce Work—It Intensifies It

2026-02-09T16:43:07+00:00

AI Doesn’t Reduce Work—It Intensifies It

Aruna Ranganathan and Xingqi Maggie Ye from Berkeley Haas School of Business report initial findings in the HBR from their April to December 2025 study of 200 employees at a "U.S.-based technology company".

This captures an effect I've been observing in my own work with LLMs: the productivity boost these things can provide is exhausting.

AI introduced a new rhythm in which workers managed several active threads at once: manually writing code while AI generated an alternative version, running multiple agents in parallel, or reviving long-deferred tasks because AI could “handle them” in the background. They did this, in part, because they felt they had a “partner” that could help them move through their workload.

While this sense of having a “partner” enabled a feeling of momentum, the reality was a continual switching of attention, frequent checking of AI outputs, and a growing number of open tasks. This created cognitive load and a sense of always juggling, even as the work felt productive.

I'm frequently finding myself with work on two or three projects running parallel. I can get so much done, but after just an hour or two my mental energy for the day feels almost entirely depleted.

I've had conversations with people recently who are losing sleep because they're finding building yet another feature with "just one more prompt" irresistible.

The HBR piece calls for organizations to build an "AI practice" that structures how AI is used to help avoid burnout and counter effects that "make it harder for organizations to distinguish genuine productivity gains from unsustainable intensity".

I think we've just disrupted decades of existing intuition about sustainable working practices. It's going to take a while and some discipline to find a good new balance.

Via Hacker News

Tags: cognitive-debt, ai-ethics, careers, ai-assisted-programming, generative-ai, ai, llms