Thoughts on OpenAI acquiring Astral and uv/ruff/ty
Autoresearching Apple's "LLM in a Flash" to run Qwen 397B locally
datasette 1.0a26
Snowflake Cortex AI Escapes Sandbox and Executes Malware
Quoting Ken Jin
GPT-5.4 mini and GPT-5.4 nano, which can describe 76,000 photos for $52
llm 0.29
Quoting Tim Schilling
Subagents
Introducing Mistral Small 4
Use subagents and custom agents in Codex
Quoting A member of Anthropic’s alignment-science team
Quoting Guilherme Rambo
Coding agents for data analysis
How coding agents work
John M. Mossman Lock Collection
What is agentic engineering?
Quoting Jannis Leidel
My fireside chat about agentic engineering at the Pragmatic Summit
1M context is now generally available for Opus 4.6 and Sonnet 4.6
Quoting Craig Mod
Shopify/liquid: Performance: 53% faster parse+render, 61% fewer allocations
MALUS - Clean Room as a Service
Coding After Coders: The End of Computer Programming as We Know It
Quoting Les Orchard
Sorting algorithms
Quoting John Carmack
AI should help us produce better code
Production query plans without production data
Perhaps not Boring Technology after all
Quoting Joseph Weizenbaum
Codex for Open Source
Quoting Ally Piechowski
Anthropic and the Pentagon
Agentic manual testing
Clinejection — Compromising Cline's Production Releases just by Prompting an Issue Triager
Introducing GPT‑5.4
Can coding agents relicense open source through a “clean room” implementation of code?
Anti-patterns: things to avoid
Something is afoot in the land of Qwen
