Fetching from the wire…
01
02
03
04
05
06
07
08
Vibe Coding2026-09-17 · source-backed
Andy "TheFlow0" Nguyen stepped down on September 16, saying the scene "used to be a group of highly talented researchers, but now it is just a bunch of noobs using LLMs and writing hacks they don't even understand." The trigger was specific rather than aesthetic: LLM-assisted contributors found a critical hypervisor bug and reported it to Sony for a bounty, closing the path for newer firmware. 318 points and 218 comments on HN. This is the clearest public case of AI-assisted contributors damaging an open-source project's goals rather than just its code quality, and the mechanism is incentives, not capability.
Each link below shares sources, entities, or timing with this story.
Starlette 1.0.0 shipped March 22, reaching stability after 8 years at 325M downloads/month as FastAPI's foundation. Simon Willison immediately identified the problem: LLMs are trained on pre-1.0 code and will generate incompatible patterns. He built a custom Claude skill from...
The decision, covered by Simon Willison, frames the ban as strategic: maintainers invest time reviewing contributions to mentor developers into trusted long-term contributors. If an LLM wrote the code, that mentorship is wasted. The wrinkle: Bun (acquired by Anthropic) runs a...
Simon Willison's September 5 TIL scripts Blender headlessly via /Applications/Blender.app/Contents/MacOS/Blender --background --python scene.py, iterating a scene across three renders at 2m39s, 3m51s and 5m59s, then stitching frames with FFmpeg. He packaged it as a reusable sk...
Simon Willison shipped it August 4, calling it the most significant release since the project launched. Companion llm-anthropic 0.26 adds Claude 5 support with server-side web search and code execution and simplifies extended-thinking configuration across variants. For scripte...
Oxide Computer CTO Bryan Cantrill published "The Peril of Laziness Lost" on April 12. His thesis: the best software exists because humans are lazy, and LLMs aren't. The argument goes like this. Larry Wall identified laziness as a programmer virtue decades ago. Not sloth. The k...
— "The defining characteristic of a coding agent is that it can execute the code it writes." Never assume LLM-generated code works without verification. Patterns for python -c edge case testing, /tmp demo files, browser automation with Playwright/Rodney. Red/green TDD: when ag...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.