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

minoscopede@lemmy.world ⁨21⁩ ⁨hours⁩ ago

I see a lot of misunderstandings in the comments 🫤

This is a pretty important finding for researchers, and it’s not obvious by any means. This finding is not showing a problem with LLMs’ abilities in general. The issue they discovered is more likely that the training is not right, specifically for so-called “reasoning models” that iterate on their answer before replying.

Most reasoning models are not incentivized to think correctly, and are only rewarded based on their final answer. This research might indicate that’s a flaw that needs to be corrected. If so, that opens the door for experimentation on more rigorous training processes that could lead to more capable models that actually do “reason”.

source
Sort:hotnewtop