Gary Marcus

Rank 14 of 47
|
Score 83
11/19/2025, 6:02:05 AM
X
In reply to:
Amrith Krishna
@krishnamrith12
·
18d
@GaryMarcus @ylecun Low information density addresses pts. 2 & 3 in your article, and this talk was made on 2016 much before your 2019 "tweet" @GaryMarcus
Exponential divergence addresses points 4 and 5, and in fact @ylecun explcitly mentions "models of world" in the talk.

https://www.youtube.com/watch?v=…
Amrith Krishna
@krishnamrith12
·
18d
@GaryMarcus @ylecun I am not sure what exactly is empty in the tweet. For instance his 2016 keynote talks about fundamental limitations of using autoregressive models, where he talks of low information density and exponential divergence
Gary Marcus
@GaryMarcus
·
18d
@krishnamrith12 @ylecun literally empty. give specifics or go home.

i came with receipts; you came empty-handed.
Amrith Krishna
@krishnamrith12
·
18d
Having followed @ylecun's works closely for a decade or so, I would have to disagree with most of the points raised in this article.
Gary Marcus
@GaryMarcus
·
18d
lecun’s persistent pattern: https://garymarcus.substack.com/…

The statement is part of a public discourse involving a debate on the contributions and recognition of ideas in the field of neural networks. It questions whether a specific acknowledgment was made by a prominent figure, which is relevant to the ongoing discussion about intellectual credit and scholarly conduct.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does not directly harm but is part of a critical discussion about academic acknowledgment.
  2. 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 questioning the acknowledgment of prior work, which is a valid part of scholarly debate. [+1]