Fetching from the wire…
Vibe Coding2026-09-26 · source-backed
The September 25 post describes running several agents at once until they couldn't explain code they were shipping, spending longer reviewing AI PRs than writing the code would have taken, and missing a basic testing error in review. After a month of hand-writing, they say they're pushing significant changes every day with more confidence. One anecdote. It sits directly opposite DHH's Rails World keynote, where he said hand-writing code "no longer makes economic sense," hasn't written a line by hand since March, and called English a better programming language than Ruby. Simon Willison split the difference the same day: coding agents "make software engineering even harder," because getting their full value "requires extraordinary discipline and knowledge." I'm with Willison. The discipline is the whole job now.
Each link below shares sources, entities, or timing with this story.
On June 22 Willison documented porting the 0.2B Moebius inpainting model to run fully client-side via WebGPU, using Claude Code to do the conversion, with a live demo. (simonwillison.net) A concrete data point on how far "small model plus coding agent plus WebGPU" has come for...
Simon Willison published a blog post today that crystallized something I've been feeling for months. The clean distinction between vibe coding (non-programmers using AI without review) and agentic engineering (professionals maintaining standards) doesn't hold up anymore. Not e...
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...
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...
Three independent sources — Simon Willison at the Pragmatic Summit, blog.tedivm.com's coding agent guide, and Anthropic's 2026 Trends Report — converged in March 2026 on the same conclusion: the highest-leverage skill in AI-assisted development is no longer prompt engineering...
Willison documented on July 4 that Opus 4.8 and Sonnet 5 can perform worse than older versions when driving bespoke file-edit tools, because they're increasingly trained and optimized for Claude Code's native editor format (Simon Willison). This is a real trap if you're buildi...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.