Comment

Feathercrown@lemmy.world ⁨11⁩ ⁨hours⁩ ago

I would advise you to do some further research on this topic. Basic keywords are “alignment problem”, “paperclip maximizer”, and “instrumental convergence”. You’re expecting a superintelligent AI to think like a human would, and that’s not likely to be the case.

source

Sort:hotnew top

Formfiller@lemmy.world ⁨11⁩ ⁨hours⁩ ago
I know it has been proven to think in terms of self preservation

source
- Feathercrown@lemmy.world ⁨11⁩ ⁨hours⁩ ago
  Being trained on human content is certainly a plus in the “it could think like us” column, but it’s no guarantee
  
  source
  - Formfiller@lemmy.world ⁨11⁩ ⁨hours⁩ ago
    We’re in uncharted territory for sure
    
    source
    Feathercrown@lemmy.world ⁨2⁩ ⁨hours⁩ ago
    What do you expect is the likelihood it shares our values enough to come to the same conclusions we would?
    
    source