Gary Marcus

Rank 13 of 47
|
Score 83
5/18/2025, 3:29:27 PM
X
In reply to:
Lawrence Chan
@justanotherlaw
·
250d
@GaryMarcus My impression is this is a result of visual capabilities being much less common during training than text-based reasoning. For many models visual tokens are added only very late in pre-training or have them grafted on only after training is complete.
Lawrence Chan
@justanotherlaw
·
250d
@GaryMarcus Your point is directionally correct though -- models have a lot easier time with the text grid than with the original screenshots; in general, they do a lot better with text reasoning than they do with images. There's a reason most of the remaining hard academic benchmarks for
Lawrence Chan
@justanotherlaw
·
250d
@GaryMarcus Reading o3's CoT (summary) is pretty illustrative -- to solve the easier one, it just looks at the board a few times; to solve the harder one, it wrote a script to turn the board into a text grid. I'll post the share link but the app tells me it doesn't support sharing convos
Lawrence Chan
@justanotherlaw
·
250d
@GaryMarcus o3 seems to be able to do both your original question and the harder one, though the harder one takes much longer (5-8 minutes it seems). Example solve for the harder one.
Gary Marcus
@GaryMarcus
·
250d
Brain teaser (not that hard for humans).

Can you get your favorite model to do it?

(I have been waiting 4 minutes on DeepSearch, no answer so far)

The statement is part of a technical discussion about AI models and their capabilities in processing visual versus text data. It offers a counterpoint to a previous assertion, suggesting that newer models may not have the same limitations. The tone is neutral and informative, contributing to a constructive dialogue.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does no harm and is part of a technical discussion. [+1]
  2. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    It promotes understanding by providing a different perspective on the capabilities of newer models. [+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.
    Engages in constructive criticism by offering a counterpoint without personal attacks. [+1]