Hacker News new | ask | show | jobs
by stri8ed 816 days ago
For programming, GPT4+. I was excited to switch to Claude after hearing all the positive anecdotes. Having tried it, I'm very unimpressed. It spouted complete, confident sounding nonsense, when I prompted it with a bug I was trying to solve. GPT4, did not get it right initially, but it was more suggestive, instead of wrongly declaring the fault, and lead me to the answer after a few more prompts. Will not be renewing my Claude subscription.
2 comments
igor47 816 days ago
This has been my experience as well. I'm surprised at how many people in the thread prefer Claude. I'm also planning to cancel my Claude subscription.

I only tried Claude because ChatGPT UI is really buggy for me (Firefox, Linux). It frequency blocks all interactions (entering new text or even scrolling) and I have to refresh the page to resume asking questions. But on Claude, it was just crashing altogether when I went to open to sidebar. Seems like traditional engineering is still a problem for these AI companies.

link
nicce 816 days ago
> I only tried Claude because ChatGPT UI is really buggy for me (Firefox, Linux).

It is buggy on every platfrom in my experience.

link
johntiger1 816 days ago
There are definitely some shills all over HN now... But even aside from that, the sheer novelty aspect (+less robotic ethical alignment) of it is enough for many
link
boringuser2 816 days ago
I think it's a little questionable to prompt language models with "bugs you're trying to solve".
link
lmeyerov 816 days ago
Curious why?

This is maybe 1/3 of my use of GPT4. Quite often, the log dump and nearby code is enough, often even without explicit instructions. Being able to do this task is similar to GitHub CoPilot code autocomplete working well too. Still not 100%, but right often enough that it flipped my use from not-at-all in GPT 3.5 to quite-often in GPT4.

link
boringuser2 816 days ago
LLMs aren't logical machines, so any non-trivial bug-fix is just likely to introduce more bugs.

It's a bit of a misunderstanding of how LLMs are supposed to be used.

One caveat is if you're very untalented, it might be able to solve very common patterns successfully.

link