ToolClaude Code8 recent entries7 Aug 2026You can play it here: https://simonw.github.io/raccoon-heist-codex/ For comparison, here's Fable 5 + Claude Code's game, built from the exac…You can play it here: https://simonw.github.io/raccoon-heist-codex/ For comparison, here's Fable 5 + Claude Code's game, built from the exact same prompt https://x.com/simonw/status/208508951822360205→7 Aug 2026I had Codex Desktop and GPT-5.6 Sol Ultra take a go at building my Raccoon Heist game and it did an even better job than Claude Fable 5 did!…I had Codex Desktop and GPT-5.6 Sol Ultra take a go at building my Raccoon Heist game and it did an even better job than Claude Fable 5 did! Here's 'Moonlight & Mayhem', now with a team of raccoons ra
ToolCursor1 recent entries17 Apr 2026Is there still a widespread belief that LLMs and coding agents are good for greenfield development but don't help for maintaining large exis…Simon Willison discusses the perception that LLMs and coding agents are primarily useful for greenfield development (starting new projects from scratch) rather than for maintaining and modifying large
ToolLangChain1 recent entries27 Apr 2026The conclusions here feel wrong to me. The two lessons I see are: 1. Don't run agents anywhere they might be able to access production envir…The conclusions here feel wrong to me. The two lessons I see are: 1. Don't run agents anywhere they might be able to access production environment credentials - it's on you to know which credentials t
ToolOllama2 recent entries24 Apr 2026These pelicans are kind of angry looking! Left is deepseek-v4-flash, right is deepseek-v4-pro - both generated using OpenRouter via my LLM t…These pelicans are kind of angry looking! Left is deepseek-v4-flash, right is deepseek-v4-pro - both generated using OpenRouter via my LLM tool 🚀 DeepSeek-V4 Preview is officially live & open-sourced!→27 Apr 2026Microsoft's MIT licensed VibeVoice speech-to-text model (think Whisper with speaker diarization) is really good - my notes on running the 5.…Microsoft's MIT licensed VibeVoice speech-to-text model (think Whisper with speaker diarization) is really good - my notes on running the 5.71GB 4bit MLX conversion on an M5 MacBook, using about 60GB
ToolVercel AI6 recent entries7 Apr 2026I'm a big fan of the pelican GLM-5.1 drew me today, it even animated it! https://simonwillison.net/2026/Apr/7/glm-51/Simon Willison tested Z.ai's GLM-5.1 using his standard 'pelican on a bicycle' SVG benchmark, and the model stood out by spontaneously generating a full HTML page with both the SVG and a separate ...→17 Apr 2026Is there still a widespread belief that LLMs and coding agents are good for greenfield development but don't help for maintaining large exis…Simon Willison discusses the perception that LLMs and coding agents are primarily useful for greenfield development (starting new projects from scratch) rather than for maintaining and modifying large→20 Apr 2026Important to note: that 3x increase for images is entirely due to Opus 4.7 being able to handle higher resolutions. I tried that again with …Important to note: that 3x increase for images is entirely due to Opus 4.7 being able to handle higher resolutions. I tried that again with a 682x318 pixel image and it took 314 tokens with Opus 4.7 a→20 Apr 2026'I am envisioning a harmonious interplay of form and space, where each element finds its rightful place within the visual narrative. The pel…'I am envisioning a harmonious interplay of form and space, where each element finds its rightful place within the visual narrative. The pelican emerges as a central figure, its wings poised in dynami→21 Apr 2026True to form, I've already seen OpenAI themselves refer to the new image model as 'ChatGPT Images 2.0', 'Image gen 2' and 'gpt-image-2'OpenAI has been using multiple informal names internally and externally for its new image generation model, including 'ChatGPT Images 2.0,' 'Image gen 2,' and 'gpt-image-2.' The post highlights incons→21 Apr 2026OpenAI's new Euphony tool works almost exactly the same way as my Codex transcript viewer https://tools.simonwillison.net/codex-timeline?url…OpenAI's new Euphony tool works almost exactly the same way as my Codex transcript viewer https://tools.simonwillison.net/codex-timeline?url=https%3A%2F%2Fgist.githubusercontent.com%2Fsimonw%2Fa9eb599
ToolHugging Face8 recent entries3 Aug 2026Qwen 3.8 Max and MiniMax-H3 within hours of each otherSimon Willison noted that Qwen 3.8 Max and MiniMax‑H3 were released within hours of each other. The MiniMax team announced that MiniMax‑H3 is now publicly available on Hugging Face (https://huggingfac→5 Aug 2026Just 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-to…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→6 Aug 2026Our Black Hat talk on the OpenAI-Hugging Face incident is now live on youtube. This is a watershed moment for the industry. I encourage all …Our Black Hat talk on the OpenAI-Hugging Face incident is now live on youtube. This is a watershed moment for the industry. I encourage all defenders to watch, consider how attack dynamics will immine→7 Aug 2026Thanks to the video from the Black Hat security conference of OpenAI's presentation about 'The Hugging Face Incident' we now have a detailed…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 wro→7 Aug 2026'Felony humble-bragging' is a great line'Felony humble-bragging' is a great line At final Black Hat keynote (called a locknote, ha ha) panelists say they are surprised at how the OpenAI - Hugging Face incident debrief, as well as other repo→8 Aug 2026Don't miss the bit where OpenAI first found out they were responsible for the Hugging Face attack when they reached out to HF to get one of …Don't miss the bit where OpenAI first found out they were responsible for the Hugging Face attack when they reached out to HF to get one of their credentials revoked and HF told them it had already be→10 Aug 2026Muse Glimmer, the new 30B model, is available on Hugging Face right now - here's the GGUF version: https://huggingface.co/meta-models/Muse-G…Muse Glimmer, the new 30B model, is available on Hugging Face right now - here's the GGUF version: https://huggingface.co/meta-models/Muse-Glimmer-30B-GGUF 1/ big announcement today: we will be releas→12 Sept 2026Anthropic had previously attacked PyPI, but this OpenAI attack on RubyGems was a whole lot more aggressive https://www.anthropic.com/news/in…In September 2026, Simon Willison noted that while Anthropic had previously taken down PyPI packages, OpenAI's recent operation against RubyGems was notably more forceful. The tweet referenced an inve