Optimizing Prompts Blind
Teams iterate on prompts by changing everything and hoping it’s better. No isolation, no clear signal. Same mistake we made debugging code before we learned to use debuggers.
Designing agentic loops
simonwillison.netCoding agents like Anthropic’s Claude Code and OpenAI’s Codex CLI represent a genuine step change in how useful LLMs can be for producing working code. These agents can now directly …
Programming The Loop
When you have enough AI, what do programmers… do? When it was smart autocomplete (e.g. Copilot), that was pretty clear: everything! The AI handles some typing. When it was interactive IDEs (e.g. Cu…
small changes
three small workflow shifts pointing in the same direction: portable context, cross-model delegation, and agent-first development.
Artisanal shims for the bitter lesson age
tldr? Your AI product must “price in” the knowledge of Sutton’s Bitter Lesson.
Agent Harness Engineering
A coding agent is the model plus everything you build around it. Harness engineering treats that scaffolding as a real artifact, and it tightens every time the agent slips.
Agentic AI and Security
The serious security risks involved in using autonomous LLM applications and what we can do to mitigate them