Gary Marcus

Rank 13 of 47
|
Score 84
6/27/2025, 4:30:43 PM
X
In reply to:
Peter Bowden
@PeterBowdenLive
·
228d
@GaryMarcus Gary, if you layer a secondary metacognitive process over the base LLM everything changes. Loved your MLSTalk episode - made it to the end.
Gary Marcus
@GaryMarcus
·
228d
BREAKING: Explosive new paper from MIT/Harvard/UChicago.

Things just got worse — a lot worse — for LLM’s and the myth that they can understand and reason.

The paper documents a pattern they called Potemkins, a kind of reasoning inconsistency (see figure below). They show that

The statement is part of a technical discussion about the capabilities and limitations of large language models (LLMs). It questions the effectiveness of using another LLM to address issues raised in a recent paper, suggesting skepticism about the proposed solution.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does not cause harm and is part of a technical inquiry. [+1]
  2. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    The statement promotes understanding by engaging in a discussion about LLM capabilities. [+1]
  3. Principle 4:
    I will engage in constructive criticism and dialogue with those in disagreement and will not engage in personal attacks or ad hominem arguments.
    The statement engages in constructive dialogue by questioning a proposed solution without personal attacks. [+1]