Gary Marcus

Rank 22 of 47
|
Score 17
Alejandro Cuadron
@Alex_Cuadron
·
319d
Surprising find: OpenAI's O1 - reasoning-high only hit 30% on SWE-Bench Verified - far below their 48.9% claim. Even more interesting: Claude achieves 53% in the same framework. Something's off with O1's "enhanced reasoning"... 🧵1/8
1/6/2025, 4:44:46 AM
X
In reply to:
Gary Marcus
@GaryMarcus
·
319d
3. Commonsense reasoning is still dodgy, as it has long been, review here, earlier today: https://garymarcus.substack.com/…
Gary Marcus
@GaryMarcus
·
319d
2. A recent paper on Putnam math problems showed a similar failure on distribution shift, showing 30% decement by o1 on math problems with minor variations eg on variable names.

Same old story, different set of problems.

https://openreview.net/forum?id=…
Gary Marcus
@GaryMarcus
·
319d
1. The problem of distribution shift, well-tested in Apple’s 2024 reasoning paper, which goes back to my own 1998 work, continues.

LLMs, like their predecessors generalize well to similar items but struggle with reliability in unfamiliar regimes, even minor variations sometimes…
Gary Marcus
@GaryMarcus
·
319d
An MIT professor just asked me, how can you be so confident that OpenAI isn’t very close to AGI?

Here is a thread of links to a several recent observations that I think show how far we are from robust intelligence.

Importantly, all of them are *known* problems, many that I…

The statement critiques the robustness of OpenAI's o1 model, suggesting that its performance may not meet expectations and that results can be fragile or hard to replicate. This is part of a broader discussion on the limitations of AI models, particularly in reasoning and handling distribution shifts.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does not cause harm; it provides a critical analysis of AI model performance. [+1]
  2. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    The statement promotes understanding by discussing the challenges in AI development, contributing to a broader conversation about AI 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 criticism, focusing on the technical aspects of AI performance without personal attacks. [+1]