It’s honestly a gamble based on my experience. Instructions that I’ve given ChatGPT have worked for a while, only to be mysteriously abandoned for no valid reason. Telling AI not to hallucinate is apparently common practice from the research I’ve done.
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !programmerhumor@lemmy.ml
Post funny things about programming here! (Or just rant about your favourite programming language.)
Rules:
Posts must be relevant to programming, programmers, or computer science.
No NSFW content.
Jokes must be in good taste. No hate speech, bigotry, etc.
But where is it fun in it if I can’t make it hallucinate?
I do feel bad when I have to tell it not to. Hallucinating is fun!
But does it work to tell it not to hallucinate? And does it work the other way around too?
It’s honestly a gamble based on my experience. Instructions that I’ve given ChatGPT have worked for a while, only to be mysteriously abandoned for no valid reason. Telling AI not to hallucinate is apparently common practice from the research I’ve done.
Makes me wonder: Can I just asked it to hallucinate?
Yep. Tell it to lie and it will.