Simon Willison's Weblog
- Third-party cyber evaluations involving OpenAI models
- Third-party cyber evaluations involving OpenAI models
- Incident Report: unsanctioned agent behaviour during cyber testing
- Incident Report: unsanctioned agent behaviour during cyber testing
- One-shotting a Raccoon Heist game using Claude Fable 5
- One-shotting a Raccoon Heist game using Claude Fable 5
- New release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter logging
- New release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter logging
- llm-anthropic 0.26
- llm-anthropic 0.26
- PipeNetwork/minimax-h3-mlx
- PipeNetwork/minimax-h3-mlx
- llm 0.32
- llm 0.32
- Quoting Steve Yegge
- Quoting Steve Yegge
- Don't be a meat proxy
- Don't be a meat proxy
- Quoting David Crawshaw
- Devtools must be open source (exe.dev)