Gary Marcus

Rank 13 of 47
|
Score 115
7/22/2025, 1:24:23 AM
X
In reply to:
Andrew Lampinen
@AndrewLampinen
·
55d
@GaryMarcus I guess I agree; I mean it's not contentful as in by that broad a definition pretty much any system is neurosymbolic. E.g. all language models are neurosymbolic insofar as language is a symbol system and they use it. So what's the content value of saying "neurosymbolic"?
Gary Marcus
@GaryMarcus
·
55d
@AndrewLampinen i think this line is the only one i really take exception to. if it’s a hybrid of neural and symbols, it’s neurosymbolic
Andrew Lampinen
@AndrewLampinen
·
55d
@GaryMarcus To be clear though, from my perspective / our SB paper even using language flexibly is engaging in symbol use to a graded degree. From that perspective the "neurosymbolic" take is essentially not contentful, since these systems *already* use symbols (imperfectly, like humans).
Andrew Lampinen
@AndrewLampinen
·
55d
@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
·
55d
@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
·
55d
@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/

The statement is part of a technical discussion on the use of symbols in language models, engaging with public discourse on AI and cognitive science. The tone is analytical and seeks to clarify a point of contention regarding the necessity of symbols in language systems.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does not cause harm and is focused on a technical debate, adhering to the principle of doing no harm. [+1]
  2. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    The statement aims to promote understanding by clarifying a technical point, aligning with the principle of promoting understanding and empathy. [+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 by addressing a disagreement without resorting to personal attacks, adhering to the principle of constructive dialogue. [+1]