Hacker News Reader

It's insane to me how you people are so confident in the LLMs abilities. Have you not tried them? They fuck things up all the time. Basic things. You can't trust them to do anything right.

But sure let's just have it generate docs, that's gonna work great.

View on HN

There's a skill to phrasing the prompt so the code comes out more reliable.

Was some thread on here the other day, where someone said they routinely give Claude many paragraphs specifying what the code should and shouldn't do. Take 20 minutes just to type it up.

Yeah sure but that's not what dude above is suggesting. Dude above is suggesting "hello ai please document this entire project for me".

I mean even if that did work you still gotta read the docs to roughly the same degree as you would have had to read the code and you have to read the code to work with it anyway.

Reply on news.ycombinator.com