Comment on Apple just proved AI "reasoning" models like Claude, DeepSeek-R1, and o3-mini don't actually reason at all.

<- View Parent
yeahiknow3@lemmings.world ⁨5⁩ ⁨weeks⁩ ago

They’re just using the terminology that’s widespread in the field. The paper’s purpose is to prove that this terminology is unsuitable.

source
Sort:hotnewtop