Gary Marcus

Rank 13 of 47
|
Score 115
7/22/2025, 1:42:05 AM
X
In reply to:
Andrew Lampinen
@AndrewLampinen
·
55d
@GaryMarcus neural nets can implement the core ingredients of intelligence without needing to have additional symbol operations explicitly built in. 2/2
Andrew Lampinen
@AndrewLampinen
·
55d
@GaryMarcus Would you say humans "need" external symbols and don't have symbols in our heads because using python sometimes helps us to (learn to) produce more accurate answers? I see the current LM (+ maybe tool) systems as a clear vindication that the connectionists were right that 1/2
Gary Marcus
@GaryMarcus
·
55d
@AndrewLampinen i have always wondered if you can really use language without symbols at all.

but the question is whether in your system you need symbols or you don’t.

i spent every year of my career until this one arguing with people (like Hinton) saying you don’t.

you obviously do.

(see
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).

The statement is part of a technical discussion on the nature of neural networks and their relationship to symbols, engaging with public discourse on artificial intelligence and cognitive science.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does not appear to cause harm and is part of a technical discussion, 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 contributes to understanding by engaging in a nuanced discussion about neural networks and symbols, promoting intellectual discourse. [+2]
  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 without personal attacks, focusing on the technical aspects of the debate. [+2]