It’s also really hard not to train it like that as people rarely ask about something they know the answer to, so the more confident it sounds while spewing bullshit the more likely it is to pass, while “I don’t know” is always unsatisfactory and gets it punished.
Comment on Study finds that Chat GPT will cheat when given the opportunity and lie to cover it up later.
hoshikarakitaridia@sh.itjust.works 11 months ago
This makes perfect sense. It’s been trained to answer questions to you satisfaction, not truthfully. It was made to prioritize your satisfaction over truth, so it will lie if necessary.
JohnEdwa@sopuli.xyz 11 months ago
GlassHalfHopeful@lemmy.ca 11 months ago
JohnDClay@sh.itjust.works 11 months ago
Misalignment always seems to be the underlying issue.
Karyoplasma@discuss.tchncs.de 11 months ago
Sometimes that fails tho.
Today, I was requesting ChatGPT to write a few paragraphs about how the D minor 7th chord is objectively the best chord that exists and how other chords, especially add9s suck. Fairly simple request to satisfy.
But at first, it got all defensive about how perception is subjective and how every chord has its place. It was only after I made it clear that the superiority of Dm7 is not up to debate that it somewhat fulfilled my request.
tdawg@lemmy.world 11 months ago
Ya it’s the fundamental issue with all of computing: Do what I mean not what I say
BearOfaTime@lemm.ee 11 months ago
Haha, nice meme.