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
[–] 2 points 7 months ago

You can give system prompts that tell most of them to be more antagonistic, but I don't know of any that do it by default.

  • permalink
  • fedilink
  • source
  • parent