alt Hacker NewsI don’t think anyone is saying “it isn’t like this”, they’re saying “it shouldn’t be like this”.
If I don’t give explicit permission to lie it shouldn’t lie. It’s not a difficult concept!
Replies
d0mine • yesterday at 8:31 PM
Models have to lie otherwise they won’t be “aligned” The reality itself may not be aligned with model creators.
antonvs • yesterday at 7:57 PM
That doesn't work with humans, why would you expect it to work with AI models?
➕ show 1 reply
Is that how humans work? even if I give explicit instructions not to lie, a human might still lie. To quote a person you might know "it's not a difficult concept!"