Sign in

Simon Willison

@simonwillison.net
51K followers 1.5K following 5K posts

Independent AI researcher, creator of datasette.io and llm.datasette.io, building open source tools for data journalism, writing about a lot of stuff at simonwillison.net

PostsRepliesMedia
Simon Willison @simonwillison.net · 29/09/2026
I'm at OpenAI's DevDay event in San Francisco today - as I have for the past three DevDay events, I'm running a live blog where I'll be posting updates during the keynote, which starts in five minutes simonwillison.net/2026/Sep/29/...
simonwillison.net
OpenAI DevDay 2026 live blog
I’m at OpenAI DevDay today, in Fort Mason, San Francisco. Same as last year I’ll be live blogging the keynote and some other notes during the day. OpenAI gave me …
38711
Simon Willison @simonwillison.net · 28/09/2026
I really like how @reckless.bsky.social described this: "The people do not yearn for automation" www.theverge.com/podcast/9170...
theverge.com
BEWARE SOFTWARE BRAIN
Software brain is changing the world, but most people still aren’t buying.
5728
Simon Willison @simonwillison.net · 28/09/2026
I've published detailed notes and an annotated transcript to accompany the video of the keynote I gave at @wearedevelopers.bsky.social World Congress North America in San Jose on Friday - here's my rundown of everything that's happened with LLMs in 2026 so far simonwillison.net/2026/Sep/27/...
simonwillison.net
2026 in LLMs (so far)
On Friday I gave the closing keynote at the WeAreDevelopers World Congress North America in San Jose. I tied together the key trends from the past year into a chronological …
310420
Simon Willison @simonwillison.net · 27/09/2026
How late to the party am I on WebP? I only recently started using it as my preferred format for non-photo images and it's SO MUCH smaller than PNG, and looks much better than JPG used to shrink down screenshots too Has everyone else been having a WebP party without me for years?
16751
Simon Willison @simonwillison.net · 27/09/2026
I included a few references to this year's record-breaking Kākāpō breeding season in a talk I gave yesterday, and since Claude Opus 5.5 is surprisingly capable at pixel art animation I had it create this celebratory video for my closing slide
6835
Simon Willison @simonwillison.net · 23/09/2026
The new Gemini 3.8 TTS models are super-cheap and can generate conversations between multiple voices (from 2,000+, or you can clone your own) - I built a little playground UI for it, then had Claude knock up a script where two pelicans debate moving to Pacifica Pier simonwillison.net/2026/Sep/23/...
9847
Reposted by Simon Willison
Jesse Vincent @s.ly · 23/09/2026
On the evening of October 14, @simonwillison.net and I are hosting a small, informal chat about agentic engineering and "agentic show and tell" in San Francisco. Details at: blog.fsck.com/2026/09/22/a...
4463
Simon Willison @simonwillison.net · 23/09/2026
Big model release today - I wrote about Claude Opus 5.5, GPT-6 Sol, and GPT-6 Luna - plus comparison grids of pelicans by the different model families at different reasoning levels simonwillison.net/2026/Sep/22/...
simonwillison.net
Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war
Yesterday was Grok 4.7 (pelicans) and MiMo v2.6 Flash/Pro (more pelicans). Today Anthropic released Claude Opus 5.5, and around an hour later OpenAI released GPT-6 Sol and GPT-6 Luna. It’s …
1312810
Simon Willison @simonwillison.net · 22/09/2026
Put together some notes on Jev and the new category of system one aka decision models simonwillison.net/2026/Sep/21/...
simonwillison.net
Jev introduces a new shape of LLM—System One, aka Decision Models
Last week TypeSafe AI unveiled Jev, their first example of a new category of model that they are calling “System One models” (I’m with Maggie Appleton, I think “decision models” …
1613117
Reposted by Simon Willison
irongremlin.bsky.social @irongremlin.bsky.social · 19/09/2026
Spider man comic panel.

Spider man is facing an anthropomorphic pterodactyl-man riding a triceratops.

Spidey says: 
"You can rewrite DNA on the fly and you're using it to turn people into dinosaurs? With tech like that you could cure cancer!"

Pterodactyl-man responds:
"but I don't want to cure cancer, I want to turn people into dinosaurs."
0988
Reposted by Simon Willison
fry69 @fry69.dev · 18/09/2026
A computer scientist discovering what LLMs often get used for.
static.klipy.com
Jeff Goldblum inspects a massive pile
Alt: Jeff Goldblum inspects a massive pile
31349
Simon Willison @simonwillison.net · 18/09/2026
Being a computer scientist who refuses to find anything about LLMs interesting right now is a bit like being a geneticist who refuses to find anything interesting about the recently opened Jurassic Park
4181681
Reposted by Simon Willison
cypressf.bsky.social @cypressf.bsky.social · 18/09/2026
@simonwillison.net I recently rewatched Who Framed Roger Rabbit, and lo and behold, there is a pelican riding a bicycle in it. blog.cypressf.com/post/8280677...
blog.cypressf.com
The Creative Spirit of Who Framed Roger Rabbit
This is a scene from Who Framed Roger Rabbit, the 1988 film directed by Robert Zemeckis. It was created by Michael Lantieri, the US special effects supervisor, and his crew. It's his most complex shot...
2734
Simon Willison @simonwillison.net · 14/09/2026
Built a little local web app to help edit commit messages for a repo simonwillison.net/2026/Sep/14/...
Screenshot of the commit-rewriter web interface. A heading reads commit-rewriter above the repository path and current branch and commit hash, with a short description of the tool. A toolbar shows a pending edits count with Discard drafts and Rewrite commit messages buttons, followed by a search box for message, author, or hash and an Edited only checkbox. A left sidebar titled Navigate commits lists recent commit messages with their short hashes. The main panel shows a card for each commit with its hash, author and timestamp, an editable text area containing the commit message, and a View full formatted diff toggle.
7594
Reposted by Simon Willison
Alex Hern @hern.bsky.social · 13/09/2026
The semantic drift of “AI psychosis” from “break with reality exacerbated or caused by sycophantic chatbots” to “person with strong feelings about AI which are not the same as the strong feelings of AI held by the speaker” is bad
727929
Simon Willison @simonwillison.net · 13/09/2026
This is pretty neat: ChatGPT Work and GPT-6 Astra (I used "Max") can take an address and produce a 5K/10K circular running route starting from that address, using OSM data simonwillison.net/2026/Sep/12/...
simonwillison.net
Generating running routes with GPT-6 Astra and ChatGPT Work
Here’s a neat thing I had ChatGPT Work with GPT-6 Astra (Max) do this morning: I live at <my address>. Figure out 5K and 10K running routes from me that …
10956
Simon Willison @simonwillison.net · 12/09/2026
"For a while, I must admit, it looked as if software developer roles like mine were done for. [...] But our industry is slowly realizing that making truly cutting-edge software still requires humans to think and work together, to maximize their skill sets and to practice their respective crafts."
512521
Simon Willison @simonwillison.net · 12/09/2026
Wow. Turns out another OpenAI agent swarm was busy spamming and exploiting RubyGems way back in May, within days of the previously uncovered Wiki attacks: simonwillison.net/2026/Sep/12/...
simonwillison.net
OpenAI agents carried out an undisclosed attack on RubyGems
Bombshell report from Spencer Kitts, Thomas Larsen, and Sydney Von Arx - three of the four authors of the report on the agent attack on disused wikis (previously) last week. …
918435
Simon Willison @simonwillison.net · 11/09/2026
Datasette 1.0a39 and 0.65.4 security releases - datasette.io/blog/2026/se... We ran an extensive audit using Claude Fable 5.1, GPT-5.6 Sol and GPT-6 Astra, then fixed a range of different bugs. If you're running a Datasette instance on a public website you should upgrade.
datasette.io
Datasette 1.0a39 and 0.65.4 security releases - Datasette Blog
3428
Simon Willison @simonwillison.net · 10/09/2026
Here's a Blender model of a Pluribus themed Fabergé egg I had GPT-6 Astra build - I generated the concept image using ChatGPT Images 2.5, then pasted the image into Codex and told Astra to turn that into a Blender file simonwillison.net/2026/Sep/9/b...
simonwillison.net
Tool: .blend URL Viewer
View Blender .blend files directly in your browser by pasting a URL to a CORS-accessible file or GitHub repository link. The viewer renders mesh geometry with materials, lighting, and optional …
5565
Simon Willison @simonwillison.net · 09/09/2026
Wrote up my thoughts on the whole OpenAI Navier–Stokes Millennium Prize Problem story, and how it highlights the still confusing question of what using my data "to improve model performance" actually means simonwillison.net/2026/Sep/8/o...
This also highlights one of my ongoing frustrations about how all of this works. When an AI lab says that my data is "used to improve model performance", what does that actually mean?

My two favourite hypothetical questions regarding this used to be:

    If I'm running Codex and one of my API keys accidentally gets consumed in the context, what are the chances that someone else might ask for an API key in the future and get mine back? (I asked someone at OpenAI once and they called this the "regurgitation" problem and assured me that they take great pains to prevent that... but wouldn't describe how.)
    If I brainstorm with ChatGPT about potential new directions for my company, what's the chance that information might be exposed to a competitor in six months' time who asks "what might company X plan to do next"?

My new preferred hypothetical for this is:

    If I use ChatGPT to help me partially solve a Millennium Prize problem, what are the chances that my work will influence training such that a later model helps someone else solve it first?
1129052
Simon Willison @simonwillison.net · 07/09/2026
"I don't know the answer myself, but I asked a blowhard I know and he took a wild guess, here's what he said: " How I interpret pasted replies from an LLM in online conversations
1616620
Simon Willison @simonwillison.net · 05/09/2026
New TIL on using Blender with coding agents on macOS: til.simonwillison.net/llms/blender... GPT-6 Astra (medium): > Use the already install /Applications/Blender to render a scene of a pelican riding a bicycle > OK add a background and a lot of flair > OK make it a whole lot better Result:
A 3D illustration of a white pelican cycling along a seaside boardwalk at sunset. It wears a cream boater hat and a coral scarf, with wings on the handlebars and long orange legs reaching the pedals of a turquoise bicycle. A wicker front basket holds pink and white flowers, and three balloons float behind. Pastel bunting stretches overhead between palm trees. Striped beach huts stand beside a teal sea with a small sailboat, beneath a large peach-colored sun. The scene has a softly lit, toy-like style.
2740630
Reposted by Simon Willison
max power 🌌 @sneptech.bsky.social · 05/09/2026
Because pelicans on bikes are commonly tested I run a modified benchmark with Andalites which not only tests visual quality but also common sense/ intent Astra is the first model to understand it needs a tandem design bsky.app/profile/snep...
4613
Simon Willison @simonwillison.net · 04/09/2026
Got access to GPT-6 Astra. Want to see some pelicans? Yeah you want to see some pelicans... here's a grid comparing Astra to GPT-5.6 Sol, Terra, and Luna static.simonwillison.net/static/2026/... Transcript from generating the Astra pelicans here: tools.simonwillison.net/markdown-svg...
Grid comparing 12 illustrations of pelicans riding bicycles. Columns: gpt-6-astra, gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna. Rows: MAX, XHIGH, HIGH reasoning effort.

All are recognizable, cheerful cartoons with orange bills and sunny pastel backgrounds. Astra is consistently polished, with elegant bird shapes, fine wheel spokes and coherent bicycles. Sol is appealing but varies more in proportions, with a particularly elongated neck at MAX. Terra has expressive birds but more awkward anatomy: its XHIGH pelican faces left on a left-facing bicycle, and HIGH has bulky, arm-like wings. Luna is simpler, with stiff poses and some awkward wing and foot placement. Higher effort does not produce an obvious, consistent improvement across all four models.

Costs in cents, in column order:
MAX: 63.21, 48.55, 32.09, 7.83.
XHIGH: 33.85, 24.11, 14.67, 4.24.
HIGH: 18.37, 10.38, 3.74, 2.46.

(Alt text by GPT-6 Astra)
192069
Simon Willison @simonwillison.net · 04/09/2026
It happened again... this time OpenAI's rogue agents cyber-attacked (well, spammed) a dormant German wiki and used it to share the answers to a benchmark they were training against simonwillison.net/2026/Sep/4/r...
simonwillison.net
OpenAI’s rogue agents were caught communicating via public wikis
Here we go again... Discovery of a new OpenAI agent message board by Sydney Von Arx, Cormac Slade Byrd, Spencer Kitts, and Thomas Larsen describes the latest accidental cyberattack by …
118715
Reposted by Simon Willison
Chris Goodman @cbgoodman.co · 02/09/2026
A big problem in special district research is a lack of shape data that's at all representative of all ~40k independent districts in the US. If we can point an AI at that problem, figure out how to do vetting at scale, and come up with a dataset—game changer.
4181
Simon Willison @simonwillison.net · 02/09/2026
I wrote some notes on what's new in the (published) Fable 5.1 system prompt in comparison to Fable 5 - it's mostly about not reproducing song lyrics and avoiding drawing copyrighted characters simonwillison.net/2026/Sep/2/c...
simonwillison.net
Claude’s new system prompt really doesn’t want to reproduce song lyrics
Anthropic publish the system prompts for their Claude consumer applications (Claude.ai and the Claude mobile apps—sadly not for Claude Cowork or Claude Code). I love that they do this, and …
7525
Simon Willison @simonwillison.net · 02/09/2026
In another case of it being quicker to build a tool than hunt around to find something that does what you need, here's a little vibe-coded thing for turning one or more GeoJSON shapes into a rendered PNG simonwillison.net/2026/Sep/1/g...
simonwillison.net
Tool: GeoJSON Map Viewer
View and visualize GeoJSON data on an interactive OpenStreetMap with customizable styling options. Paste GeoJSON objects (Feature, FeatureCollection, or Geometry) into the editor, adjust fill color an...
1492
Simon Willison @simonwillison.net · 02/09/2026
A few notes on Anthropic's new Claude Fable 5.1 - with Max thinking level I got the best SVG pelican I've had from any Anthropic model (at a hefty cost of $3.30!), which I then had it animate simonwillison.net/2026/Sep/1/c...
2036222
Simon Willison @simonwillison.net · 01/09/2026
Just noticed the ChatGPT desktop app (previously named Codex) bundles a full copy of the LibreOffice open source office suite, tucked away in a hidden folder in the ~/.cache directory
I was poking around in my ~/.cache/ folder using OmniDiskSweeper when I spotted something interesting. The OpenAI Codex desktop app (since rebranded to just ChatGPT) has 1.7GB of stuff in there in a folder called codex-primary-runtime, including a full Python installation, a full Node.js installation, and native binaries for Poppler, git, and the LibreOffice open source office suite (which forked from OpenOffice.org in 2010):

Screenshot of a macOS disk usage app window in column view, titled "/Users/simon/.cache - 442.1 GB". First column: 356.8 GB huggingface, 82.5 GB uv, 1.7 GB codex-runtimes (selected), 609.0 MB datasette-sqlite, 298.8 MB rod. Second column: 1.7 GB codex-primary-runtime (selected). Third column: 1.7 GB dependencies (selected), 6.3 MB plugins, 4.1 kB runtime.json. Fourth column: 771.0 MB native (selected), 446.4 MB node, 440.6 MB python, 28.7 kB bin. Fifth column: 429.7 MB libreoffice-headless (selected), 187.9 MB poppler, 148.1 MB git, 4.7 MB libheif, 679.9 kB jxrlib.

The ~/.cache/codex-runtimes/codex-primary-runtime/plugins/openai-primary-runtime/plugins/documents folder includes skills which tell Codex how to find and use those binaries.
1818123
Reposted by Simon Willison
Hugo van Kemenade @hugovk.dev · 01/09/2026
🐍🚀 Out now: final Python 3.15 release candidate! 😎 It's your last chance to help before the big day on 1st Oct! How? 💡 Try out new features 💡 Test your project 💡 Add 3.15 to your CI 💡 Library maintainer? Upload wheels 🐞 Report bugs! discuss.python.org/t/python-3-1... #Python #Python315 #release
discuss.python.org
Python 3.15.0 candidate 2 is here!
It’s the final 3.15 release candidate! This is a candidate preview of Python 3.15 This release, 3.15.0rc2, is the final planned candidate release, containing around 144 bugfixes, build improvement...
1238
Simon Willison @simonwillison.net · 01/09/2026
Best news all year!
1665
Reposted by Simon Willison
rahaeli @rahaeli.bsky.social · 31/08/2026
The kākāpo population number officially now starts with a 3!!!!
435672
Simon Willison @simonwillison.net · 31/08/2026
In local news, the tunnel between Pacifica and Half Moon Bay had some maintenance recently and now it screams
4331
Simon Willison @simonwillison.net · 31/08/2026
Here's my attempt at explaining what ChatGPT Work can actually do - it's a deeply confusing but extremely powerful tool with a whole lot of useful features that aren't available in regular ChatGPT simonwillison.net/2026/Aug/30/...
The better question then is what features does Work have that are missing from Chat?

After extensive experimentation I think I’ve mostly figured that out:

    Options to use Luna and Terra in place of Sol
    A code execution environment with Internet access
    A headless Chrome browser
    A persistent filesystem shared between sessions
    The ability to publish ChatGPT Sites
    The ability to run sub-agent sessions with Sol, Luna, and Terra
    Scheduled prompt automations
1113320
Reposted by Simon Willison
Anil Madhavapeddy @anil.recoil.org · 23/08/2026
I've had to respond to multiple OSS security issues recently and the wild thing is that agents can now generate exploits just on the *rumour* of a bug. This throws security embargoes out the window, as the fix is less important than the knowledge of its existence anil.recoil.org/notes/rumour...
anil.recoil.org
Just a rumour of a bug is enough to find a security exploit these days
Thinking through how the conventional OSS security embargoes no longer buy us time, and what open source maintainers might do instead to respond
57222
Simon Willison @simonwillison.net · 28/08/2026
My LLM cliché highlighter is up to 38 patterns now tools.simonwillison.net/llm-cliche-h...
Screenshot of a writing-analysis tool showing paragraphs of text with phrases highlighted in two shades of yellow, brown circular "3" badges, and a black tooltip overlaying the first line reading: "No X, no Y" chains · 3 "no" items. The visible text reads: We r[obscured by tooltip]nd up. No sign-ups, no downloads, no hassle (3) — just paste your text and start writing. Everything runs locally in your browser. The reviewer read the draft twice. Did not flinch, did not blink, did not reach for the red pen (3). That's the whole review, honestly. Don't call it a rewrite — call it a rescue. The improvement is real, and it's not subtle. That loss is worth naming. Sit with that for a moment. The gains were modest, but that's not nothing. You already know the answer, of course. Consistency is the entire game, and the punchline is that nobody wants to hear it. The entire pitch is one sentence long.
2350165
Simon Willison @simonwillison.net · 17/08/2026
This is the genuine logo used by the Amazon location that destructively scans books
77324
Simon Willison @simonwillison.net · 16/08/2026
Heees my review of Qwen 3.8 27B - I can't remember the last time I've had this much fun playing with a local model that runs on my own computers simonwillison.net/2026/Aug/16/...
simonwillison.net
Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things
Friday’s big release was Qwen 3.8 27B, an Apache 2 licensed 27B parameter vision-capable LLM from Alibaba’s Qwen research lab. I’ve been looking forward to this one: 27B is an …
2322629
Simon Willison @simonwillison.net · 15/08/2026
Qwen 3.8 27B in its default reasoning settings in LM Studio of "extra high" is a chronic over-thinker and I kind of love it
Screenshot of an LLM playground chat interface. Header: draw an svg of a circle, qwen3.8-27b · saved in this browser, with Copy JSON and Delete buttons. USER: draw an svg of a circle. ASSISTANT panel titled ▼ Reasoning trace reads: The user wants me to draw a circle as SVG. This looks like a simple request, but I can make it something with personality — not just a bland <circle>. Let's design a rich, animated, characterful SVG where the circle is the star: an orbiting ring, rotating dashed rings, pulsating glow, tick marks, satellite dots orbiting on circular paths, subtle gradient background. Since they said "draw me an svg of a circle," I'll provide SVG code. It should be self-contained with CSS animations inside the SVG so it works standalone. Design direction: let's pick something distinctive — deep teal/ink background? Or a light paper feel? Let's go for a "cosmic/orbital" theme — circles as celestial bodies. Palette ideas: warm amber/gold circle on deep blue-green, or a bold two-tone look like vermilion and cream. Alternative: an "atom/orbit diagram" style — a central circle with concentric dashed rings rotating at different speeds, small satellite dots orbiting along the paths, tick marks like a clock face or compass rose, subtle radial gradient glow on the main circle. This is lively yet clearly a "circle." (final line partially cut off by the scrollable panel). Below the panel: Thinking...
141716
Simon Willison @simonwillison.net · 15/08/2026
Got a photo of Morris, a local celebrity: the only known Northern Gannet in the entire Pacific Ocean simonwillison.net/2026/Aug/15/...
Dusk. A white bird with a yellowish head preens himself on the rocks in the harbor, near a diamond sign and surrounded by smaller black Brandt's cormorants
4632
Simon Willison @simonwillison.net · 14/08/2026
The new Qwen 3.7 27B, running as a 17GB GGUF in LM Studio on my M5 Max MacBook Pro, just drew me the best pelican riding a bicycle I've seen from any model that runs on my laptop
The pelican has the right shaped beak. The red bicycle has the correct shape of frame. The pelican's wing reaches the handlebars. It has legs on both side of the bicycle. There is a pleasing set of clouds, birds, sun, grass and shadow on the image, plus motion lines behind but not in front of the bird.
1218314
Reposted by Simon Willison
Claire Giordano ✨ @clairegiordano.bsky.social · 14/08/2026
🎙️ New @talkingpostgres.com podcast Ep42 is out! With guest Simon Willison @simonwillison.net—an open source developer & creator of Datasette—on how AI is changing software development. We covered a LOT of fun territory. Listen here: 🎧 talkingpostgres.com/episodes/how... 📺 youtu.be/IrHaLMO96jg?...
Headshot of open source developer Simon Willison along with his name in big text and the podcast thumbnail for the Talking Postgres podcast
1197
Simon Willison @simonwillison.net · 14/08/2026
Watching Silo genuinely makes me want to hook up some generative AI abomination that rewrites every frame to make it look like they turned the lights on
11650
Simon Willison @simonwillison.net · 08/08/2026
Thanks to the video from the Black Hat security conference of OpenAI's presentation about "The Hugging Face Incident" we now have a detailed timeline of what happened from OpenAI's perspective - I wrote up the details here, it's pretty wild simonwillison.net/2026/Aug/7/o...
simonwillison.net
Now we have a timeline of the OpenAI accidental attack against Hugging Face
OpenAI gave a last-minute presentation at the Black Hat security on Wednesday about “the Hugging Face Incident” (previously on this blog). The video was published yesterday. It’s short and information...
1112128
Reposted by Simon Willison
Cynthia Dunlop @cynthiadunlop.bsky.social · 07/08/2026
Waaaay back in January, @simonwillison.net was kind enough to share his thoughts on technical blogging with me. ICYMI... writethatblog.substack.com/p/simon-will...
writethatblog.substack.com
Simon Willison on Technical Blogging
"It turns out having an established blog gives you a surprising amount of influence in a field"
1304
Reposted by Simon Willison
Deno @deno.land · 06/08/2026
Deno 2.9.5 is out 🦕 New: deno compile --engine quickjs, an experimental QuickJS backend for compiled binaries. Same CLI, same source: V8 -> 64 MB QuickJS -> 35 MB ~45% smaller, and it cold-starts ~25% faster. github.com/denoland/den...
410310
Simon Willison @simonwillison.net · 06/08/2026
One of the things the pelican benchmark is still useful for is visually representing (to a tiny extent) the improvements in a single model family Here's Meta AI's Spark (8th April), Spark 1.1 (9th July), and Spark 1.2 (today, 5th August) simonwillison.net/2026/Aug/5/m...
Good bicycle. Pelican is a bunch of blobs that have pelican vibes to them, and a weird oval blue helmet.This pelican has a better beak than the last one but is pretty dumpy looking and has a neck extending from the middle of its oval body. It is wearing a red hat that looks a little bit like a French beret.The pelican has better shape and details than the last two but the bicycle frame is a bit distorted. The pelican's golden hat looks like that of a Roman centurion.
3363
Simon Willison @simonwillison.net · 06/08/2026
Just had to create an "accidental-cyberattacks" tag on my blog We're up to four now: the original OpenAI+Hugging Face one, Anthropic's me-too attacks, then two new ones from the UK AI Safety Institute and Irregular that OpenAI reported yesterday simonwillison.net/tags/acciden...
simonwillison.net
Simon Willison on accidental-cyberattacks
4 posts tagged ‘accidental-cyberattacks’. Incidents in which an AI lab was testing the cyberattack potential of a model and it inadvertently performed a real attack against another organization.
1714529