Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

My opinion on Claude as ChatGPT user.

It feels like ChatGPT on cocaine, I mean, I asked for a small change and it came with 5 solutions changing all my codebase.



Is this the one that goes 'Oh no, I accidentally your whole codebase, I suck, I accept my punishment and you should never trust me again' or is that a different one?

I seem to remember the 'oh no I suck' one comes out of Microsoft's programmer world? It seems like that must be a tough environment for coders if such feelings run so close to the surface that the LLMs default to it.



Was it Sonnet or Opus? I've found that Sonnet will just change a few small things, Opus will go and do big bang changes.

YMMV, though, maybe it's the way I was prompting it. Try using Plan Mode and having it only make small changes.


Is this opinion on claude code or claude the model?


I'm NOT saying it is, but without regulatory agencies having a look or it being open source, this might be well working as intended, since Anthropic makes more money out of it.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: