Apple just proved AI "reasoning" models like Claude, DeepSeek-R1, and o3-mini don't actually reason at all. They just memorize patterns really well.
Apple just proved AI "reasoning" models like Claude, DeepSeek-R1, and o3-mini don't actually reason at all. They just memorize patterns really well.
LOOK MAA I AM ON FRONT PAGE
You're viewing a single thread.
251
comments
Would like a link to the original research paper, instead of a link of a screenshot of a screenshot
251
comments