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

• spankmonkey@lemmy.world ⁨2⁩ ⁨weeks⁩ ago

  I agree with the author.

  If these models were truly “reasoning,” they should get better with more compute and clearer instructions.

  The fact that they only work up to a certain point despite increased resources is proof that they are just pattern matching, not reasoning.

  source

  • auraithx@lemmy.dbzer0.com ⁨2⁩ ⁨weeks⁩ ago

    Performance eventually collapses due to architectural constraints, this mirrors cognitive overload in humans: reasoning isn’t just about adding compute, it requires mechanisms like abstraction, recursion, and memory. The models’ collapse doesn’t prove “only pattern matching”, it highlights that today’s models simulate reasoning in narrow bands, but lack the structure to scale it reliably. That is a limitation of implementation, not a disproof of emergent reasoning.

    source

    • technocrit@lemmy.dbzer0.com ⁨2⁩ ⁨weeks⁩ ago

      Performance collapses because luck runs out. Bigger destruction of the planet won’t fix that.

      source

      • auraithx@lemmy.dbzer0.com ⁨2⁩ ⁨weeks⁩ ago

        Brother you better hope it does because even if emissions dropped to 0 tonight the planet wouldnt stop warming and it wouldn’t stop what’s coming for us.

        source

        • -> View More Comments
• technocrit@lemmy.dbzer0.com ⁨2⁩ ⁨weeks⁩ ago

  The paper doesn’t say LLMs can’t reason

  Authors gotta get paid. This article is full of pseudo-scientific jargon.

  source