Hacker News Reader

The regular ChatGPT 5 seems pretty reliable to me? I ~never get crazy output unless I'm pasting a jailbreak prompt I saw on twitter. It might not always meet my standards, but that's true of a lot of things.

View on HN

Maybe not the same thing, but chatgpt 5 was driving me insane in visual studio co pilot last week. I seemingly could stop it from randomly changing bits of code, to the point where it was apologising then doing the same in next change even when told not to.

I've now changed to asking where things are in the code base and how they work then making changes myself.

Deleting comments even when instructed not to do so is another failure mode. They definitely require more fine-tuning in these cases.

Reply on news.ycombinator.com