144
AI overly affirms users asking for personal advice— Not only are AIs far more agreeable than humans when advising on interpersonal matters, but users also prefer the sycophantic models. (news.stanford.edu)
submitted 7 months ago by to c/technology@lemmy.world
17 comments fedilink hide all child comments
 

Research.

you are viewing a single comment's thread
view the rest of the comments
[–] 1 point 7 months ago

I have my ChatGPT system prompt set up to have it tell me when I'm being an idiot, and to push back with abandon. Seems to be working out so far.

  • permalink
  • fedilink
  • source
  • parent