▲ 492 ▼ Apple study exposes deep cracks in LLMs’ “reasoning” capabilities (arstechnica.com) submitted 2 years ago by misk@sopuli.xyz to c/technology@lemmy.world 105 comments fedilink hide all child comments
[–] Saik0Shinigami@lemmy.saik0.com 1 point 2 years ago I’d say Gemma 2B wasn’t actually wrong I call that talking itself out of being correct. permalink fedilink source parent