News for hackers. Stuff that matters.
Re:Cursor CLI by eru on Friday August 08, 2025 @01:01AM (#44833603)
> It would force me to have a useful, up to date document about how to build, run, and edit my projects.

Not really: our AI agents are probably smart enough to even make sense of somewhat bad instructions.

Re:Cursor CLI by yunohn on Friday August 08, 2025 @02:15AM (#44834034)
They’re definitely not, Claude and all other agents frequently forget the build and test commands present in CLAUDE/etc.md for my various repos (even though most of them were were initialized by the AI).
Re:Cursor CLI by eru on Friday August 08, 2025 @03:12AM (#44834379)
Whether Claude and co understand is probably not a great proxy for whether your docs are good for humans.
Re:Cursor CLI by yunohn on Friday August 08, 2025 @07:35AM (#44835842)
Hmmm, in my experience if something like documentation confuses the current SOTA LLMs, then it will confuse the average developer for sure.
Re:Cursor CLI by eru on Sunday August 10, 2025 @03:12AM (#44853365)
I had the other direction in mind: you can put together some text that the average LLM will figure out, but that will be really annoying for your average developer.

Eg if you write your instructions in a mixture of base 64, traditional Chinese, morse code and Polish, the LLM will still figure it out.

Re:Cursor CLI by dotancohen on Friday August 08, 2025 @05:07AM (#44834978)
Not the case at all. AI agents will happily turn your bad ideas into code.
Re:Cursor CLI by eru on Friday August 08, 2025 @07:05AM (#44835629)
Non sequitur?

I am talking about LLMs figuring out how to build your project with some bad and incomplete instructions plus educated guessing.