top | item 45867846 (no title) phoerious | 3 months ago I'm just an AI researcher, what do I know? discuss order hn newest blibble|3 months ago > I'm just an AI researcher, what do I know?me too! what do I know?(at least now we know where the push for this dreadful policy is coming from) phoerious|3 months ago The whole purpose RLVR alignment is to ensure objectively correct outputs.
blibble|3 months ago > I'm just an AI researcher, what do I know?me too! what do I know?(at least now we know where the push for this dreadful policy is coming from) phoerious|3 months ago The whole purpose RLVR alignment is to ensure objectively correct outputs.
blibble|3 months ago
me too! what do I know?
(at least now we know where the push for this dreadful policy is coming from)
phoerious|3 months ago