top | item 47133045 (no title) aanet | 5 days ago Sorry, I LOL'd.This is too funny to not laugh at the absurdity of "safety and alignment" researchers blindly trusting agents like Claw without fully understanding. Or maybe they were researching. discuss order hn newest Kiboneu|5 days ago Yeah. Pretty careless from the lenses of AI safety research. Considering this is from a team at Meta, it’s not surprising that it is roleplaying.
Kiboneu|5 days ago Yeah. Pretty careless from the lenses of AI safety research. Considering this is from a team at Meta, it’s not surprising that it is roleplaying.
Kiboneu|5 days ago