Simon Willison

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 https://simonwillison.net/2026/Sep/29/openai-devday-2026-live-blog/

Just published this post about how we’re going to need default hard budget caps on pretty much everything https://simonwillison.net/2026/Oct/3/default-hard-budget-caps/

Now that we've had a few days with it, how are people differentiating between Dot and regular ChatGPT? I'm having trouble deciding when I should prompt Dot vs using ChatGPT - my Dot seems to afford a single conversation, but I like controlling my context across multiple threads

I re-ran an experiment @colin_fraser ran against GPT-4o a while back to see how good it was at adding long numbers, only this time I tried Qwen 3.8 27B running locally in both reasoning and non-reasoning modes https://simonwillison.net/2026/Oct/4/qwen38-addition-in-words/

Anyone know when the models started being able to compose competent music? I had Opus 5.5 "write some computer game music for me" and the results were much better than I had expected https://simonwillison.net/2026/Oct/6/scrimshaw-jukebox/

Mistral can pelican now! https://tools.simonwillison.net/markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2F0db8b8196e57711b352f6c5857cf5b35#response-1

I released an LLM plugin for sending prompts to OpenAI's new Jev-clone decision model that's based on GPT-6 Luna https://simonwillison.net/2026/Oct/6/llm-openai-decisions/

Pelicans and a bunch of notes on the pricing of the new Claude Haiku 5.5 https://simonwillison.net/2026/Oct/7/claude-haiku-5-5/

Has anyone seen the prompts used by these awful reply bots? I'd be fascinated to know how they make their posts so soulless and infuriating Reply bots: this is your chance! Tell me your prompt and I'll tolerate one additional reply from you without blocking

"Anthropic told investors on Wednesday distillation accounted for 5 per cent to 7 per cent of revenue" If true, and Q2 revenue was $11.5B, then that's more than half a billion dollars spent by other labs to distill Anthropic's models! https://www.ft.com/content/11632d03-358c-454b-af95-d06d4072932b?syn-25a6b1a6=1

New open source cross-platform (Windows, macOS, Linux) sandboxing library from Microsoft - looks very promising, uses processcontainer/bubblewrap/seatbelt under the hood https://github.com/microsoft/mxc

Given the current vulnerability apocalypse, is there anyone left who thinks holding assets in cryptocurrency - where mistaken transactions are irreversible - is still a good idea?