Simon Willison's Weblog
- llm-anthropic 0.29
- llm-typesafe 0.1a0
- Jev introduces a new shape of LLM - System One, aka Decision Models
- Cloudflare Python Workers are now generally available
- Quoting voxium
- MCP was always a bad idea?
- llm-keys-ui 0.1
- datasette-explain 0.2.2
- datasette-auth-github 1.0
- California Sea Lion, Brandt's Cormorant
- Gemini Hacked Three Companies in First Known Breakout by Google’s AI
- Note on 18th September 2026
- Quoting Thariq Shihipar
- The Creative Spirit of Who Framed Roger Rabbit
- Be alert: targeted attacks on prominent Rustaceans
- How To Write With An LLM
- Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint
- Self-generated prompt injections in compaction summaries
- datasette 1.0a40
- datasette 0.65.5