Comment

Comment by morsecodist

This matches my experience exactly. "poisoned" is a great way to put it. I find once something has gone wrong all subsequent responses are bad. This is why I am iffy on ChatGPT's memory features. I don't notice it causing any huge problems but I don't love how it pollutes my context in ways I don't fully understand.

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton