alt Hacker NewsThey invited AI in by creating a comprehensive list of instructions for AI agents - in the README, in a context.md, and even as yarn scripts. What did they expect?
Replies
ggbaker • today at 1:28 AM
The CONTEXT.md file was created 5 months ago, and the contribution policy changed today. I would interpret that as a good-faith attempt to work with AI agents, which with some experience, didn't work as well as they hoped.
Seattle3503 • today at 8:08 AM
I still find it useful to vibe code in a private fork. For example with yt-dlp its now super easy to add a website with Claude for personal use, but that doesn't mean it's appropriate to open a PR.
embedding-shape • today at 1:07 AM
Wouldn't that be for their usage? It's presence doesn't implicitly mean they want incomplete PRs submitted to their repository constantly.
Hey, Steve from tldraw here. We use AI tools to develop tldraw. The tools are not the problem, they're just changing the fundamentals (e.g. a well-formed PR is no longer a sign of thoughtful engagement, a large PR shows more effort than a small PR, etc) and accelerating other latent issues in contribution.
About the README etc: we ship an SDK and a lot of people use our source code as docs or a prototyping environment. I think a lot about agents as consumers of the codebase and I want help them navigate the monorepo quickly. That said, I'm not sure if the CONTEXT.md system I made for tldraw is actually that useful... new models are good at finding their way around and I also worry that we don't update them enough. I've found that bad directions are worse than no directions over time.