Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-03-03 · source-backed
Willison's evolving "Agentic Engineering Patterns" series introduces two critical concepts. "Cognitive debt" — the danger of losing understanding of agent-generated code — is a distinct and more dangerous cousin of technical debt because you can't debug what you don't understand. "Knowledge hoarding" — the argument that domain expertise (knowing what's possible) is the irreplaceable skill in an agentic world. He demonstrated both by building a GIF optimizer with Gifsicle WASM, showing how experienced developers expand into unfamiliar domains by maintaining the architectural judgment layer. This is becoming the canonical practitioner reference. simonwillison.net
Each link below shares sources, entities, or timing with this story.
Mario Zechner wrote an essay. Simon Willison amplified it. The core argument: agentic code generation creates "cognitive debt," where mistakes compound faster than humans can review them, and the speed that makes agents attractive is precisely what makes their failures catastr...
Willison shipped datasette-agent-edit 0.1a0 on June 7, letting agents perform structured data edits inside Datasette, alongside micropython-wasm sandbox work for running untrusted agent code. Separately his evolving Agentic Engineering Patterns guide reframes the work around t...
Simon Willison has been writing software for over 25 years. He's one of the most disciplined, transparent engineers in the Python ecosystem. And yesterday he published an essay admitting he no longer reviews every line of code that Claude Code generates for his production proj...
Simon Willison spent a while taking ChatGPT Work apart and published the map on August 30. Work splits into Work Cloud and Work Local, the latter being the renamed Codex desktop app, at $20/month and up since July 9. He enumerates six capabilities Work has that Chat doesn't, a...
Spotify's Portal team published Xirp on August 10: a vendor-neutral agentic development environment that manages concurrent sessions across Claude Code, Gemini CLI, and Codex, each session isolated in its own git worktree so dozens of agents can work the same codebase without...
Willison published his AI Engineer World's Fair conversation with Anthropic's Cat Wu and Thariq Shihipar, covering Claude Code, Claude Tag, and Fable. Primary-source practitioner conversation with the people who actually build the thing, rather than secondary coverage of a pre...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.