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
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/...
"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…
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/...
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…
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…
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…
"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
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…
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…
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...
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…
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…
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…
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
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…
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/...
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
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
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…
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…
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…
Four years ago today I tweeted a concept for a "Raccoon Heist" video game, product description generated by GPT-3 and concept "art" created by DALL-E Today I fed those assets into Fable 5 and had it build full working…
Big new release of my LLM CLI tool and Python library for talking to hundreds of different LLMs - reasoning traces, OpenAI Responses support, server-side tools, smarter logging and a whole lot more…
The MiniMax-H3 video generation model is a lot of fun - here's what I generated on my M5 Pro Mac for the prompt "a rainbow colored skunk leaps over a mossy log in a supermarket" (~115GB model download, took around 45…
Question for dog companions: are you aware that "nose work" is a sport you can participate in with your dog? We've been doing it with Cleo and it is ABSURDLY fun. Dogs have to find 3 different official hidden scents…
Here's my attempt at summarizing the various "open letters" about AI development that have been doing the rounds over the past few weeks simonwillison.net/2026/Aug/2/o...
Got a disappointing pelican from DeepSeek-V4-Flash-0731 at default reasoning mode - on the left - but then I bumped reasoning up to high (via OpenRouter) and got the much better one on the right…
The new stateless MCP specification has rekindled my interest in MCP, and inspired some new projects, including mcp-explorer and datasette-mcp simonwillison.net/2026/Jul/31/...
I'm on Oxide and Friends podcast this week! We talked about accidental cyberattacks, Kimi K3, Golden Gate Claude, Zizians, Alameda wild turkey attacks, Soviet Marburg virus research, the Lead-crime hypothesis, and a…
I've been working with Prime Radiant building a new tool for running small eval suites against models, harnesses, and prompts - it's called "smevals", you can try it with "uvx smevals docs", and I wrote about it here…
Your infrequent reminder that if you live near the San Francisco Bay Area you should go to Moss Landing (south of Santa Cruz) and rent kayaks there, because the estuary is full of sea otters and you will encounter…
A new TIL on adding custom MCP servers to both the ChatGPT and Claude regular chat interfaces - it's a little less obvious than I had hoped, but I got there in the end til.simonwillison.net/llms/mcp-in-...
Hugging Face just published a highly detailed technical account of OpenAI's accidental cyberattack on their systems - it's wild how sophisticated this was: huggingface.co/blog/agent-i... Wrote up some of my own notes…
Ruff 0.16.0 - Astral's fast Python linter - came out a few days ago and increased the number of default-enabled rules from 59 to 413, which highlighted all sorts of problems across my projects (1618 in sqlite-utils…
I wrote about the completely wild incident where OpenAI were testing a new model and it broke out of its sandbox and broke INTO Hugging Face to steal the answers to the benchmark simonwillison.net/2026/Jul/22/...
San Francisco tip: it only costs around $15 ($10 in quarters plus a $5 bill for the self-playing violin) to activate every single Orchestrion in Musée Mécanique
I interviewed Cat Wu and Thariq Shihipar from the Claude Code team at the AI engineer World's Fair a couple of weeks ago - the video is now out, so I've published an annotated transcript of our conversation…
If you have Claude Code installed you're running software that uses the new (unreleased) version of Bun that's been rewritten in Rust - here are two commands you can run to see that for yourself…
Suggestion for hyperscalers feeling pressure over data center water use: Buy up a few exclusive country clubs, convert the golf courses into public parks, pay for guides and binoculars to get the previous members into…