Gary Marcus

Rank 14 of 47
|
Score 83
11/20/2025, 8:40:26 PM
X
In reply to:
Jürgen Schmidhuber
@SchmidhuberAI
·
15d
25 years later, @ylecun's 2015 slide rehashed the 1990 paper on a recurrent neural "world model" that predicts all sensory inputs including pixels and multi-dimensional reward signals & pain signals:
J. Schmidhuber. Making the world differentiable: On using fully recurrent
Yann LeCun
@ylecun
·
15d
I first showed a version of this slide in 2015.
It was also part of my NIPS 2016 keynote.

The statement is part of a discussion on AI research, specifically addressing the originality of ideas presented in a slide by a prominent AI researcher. The tone is somewhat critical, suggesting that the metaphor used in the slide was at least new, implying that other aspects may not have been. This engages in public discourse by discussing the evolution and originality of ideas in AI, a significant field of public interest.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does not cause harm but implies criticism of originality, which is a common aspect of academic discourse.
  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 focusing on the originality of the metaphor, avoiding personal attacks. [+1]