24
Do LLMs "have" the "abillity" to be told they are wrong or incorrect and be able to contest that? (lemmy.world)
submitted 1 month ago by to c/asklemmy@lemmy.ml
34 comments fedilink hide all child comments
 

I think i've only once flat out told one it was wrong about a specific assertion I quoted and it immediately was able to find its way to what I knew to be the correct claim.

I just wonder what would happen if i was in fact mistaken and I told it confidently it was wrong without elaborating

you are viewing a single comment's thread
view the rest of the comments
[–] 16 points 1 month ago (2 children)

The pandering is really unnerving when you’re not used to it. I’ve used chatGPT only once and it was to edit my resume since I hate doing that. It helped with consistency and wanted active verbs in there which was fine. It was the constant compliments at the top of every response that was so weird. Like I’m asking for feedback, not to hear how wonderful of a writing job I already did. I felt like I was being handled like an oversensitive child.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 11 points 1 month ago* (1 child)

    That's a great observation —the sycophantic nature of ChatGPT can be really offputting when you're not used to the way the AI writes. Would you like:

    • tips and tricks on using ChatGPT?
    • advice on creating your own GPT prompt?
    • suggestions on less sycophantic AI chatbots?

    I'm here to help. Just let me in

    can't do it anymore the bit isnt worth it ew ew ew

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •