Gary Marcus

Rank 13 of 47
|
Score 115
7/22/2025, 12:44:30 AM
X
In reply to:
Andrew Lampinen
@AndrewLampinen
·
56d
@GaryMarcus program to answer a question, then run it); and I think that's a good thing. Often, such systems don't need tools a
at test time — even if they help learning; just as a math student might have used Matlab or whatever in some classes but can still answer test questions without it.
Andrew Lampinen
@AndrewLampinen
·
56d
@GaryMarcus Regarding 2) I obviously can't say more than is public (and I didn't work on the IMO project so I don't know the details). But I think the general point I want to make is that the LM paradigms are moving towards using classic symbol systems as tools (e.g. write a quick Python 4/
Andrew Lampinen
@AndrewLampinen
·
56d
@GaryMarcus But my critique isn't so much about the words but the *approach* in which deep learning is embedded in a symbolic reasoning system, which I'm suggesting is the opposite of how humans (e.g. in math) work: a messy system using symbols as tools to solve certain kinds of problems 3/
Andrew Lampinen
@AndrewLampinen
·
56d
@GaryMarcus You have made similar flavors of statements to that in the past, e.g. in this quote from https://arxiv.org/abs/1801.00631 — though I agree your phrasing is more careful than some. 2/
Andrew Lampinen
@AndrewLampinen
·
56d
@GaryMarcus Thanks!
1) I was trying to distill a sentiment, thinking of papers like these:
https://arxiv.org/abs/2305.00813
https://openreview.net/forum?id=…
E.g. "neural network[s ...] effectively model machine perception, symbolic knowledge-based AI is better suited for modeling machine cognition. " 1/
Gary Marcus
@GaryMarcus
·
56d
@AndrewLampinen Andrew, fascinating thread. Two questions,

1. Who has actually argued “Even now, (neuro)symbolic advocates often argue that pure symbol manipulation is the only "real" intelligence, and "messy" deep learning should just be an input to symbol manipulation”? I consider myself to

The conversation involves a discussion on the integration of deep learning and symbolic systems, touching on the effectiveness of neurosymbolic AI. The participants are engaging in a technical debate about AI methodologies, referencing academic papers and theories.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The discussion is technical and does not appear to cause harm. It is a professional exchange of ideas.
  2. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    The conversation promotes understanding and empathy by engaging in a thoughtful exchange of ideas about AI methodologies. [+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 participants engage in constructive criticism and dialogue, focusing on the technical aspects of AI without resorting to personal attacks. [+1]