Gary Marcus

Rank 17 of 47
|
Score 78
4/10/2024, 3:20:14 PM
X
In reply to:
Derya Unutmaz, MD
@DeryaTR_
·
540d
@GaryMarcus Not true:
Wen-Ding Li
@xu3kev
·
541d
A big jump in math/reasoning for our coding benchmark 🤯 https://livecodebench.github.io/…
Gary Marcus
@GaryMarcus
·
541d
Classical symbolic software: fix one component while holding others constant

LLMs: fix one component, break others, often unpredictably
TheLobbyistGuy
@TheLobbyistGuy
·
541d
@GaryMarcus Massive degradation in coding.

The more “alignment” they do, the worse the performance gets.

The statement is a critique of AI model performance and the lack of detailed disclosure from developers, contributing to public discourse on AI development and transparency.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does no harm. [+1]
  2. Principle 2:
    I will respect the privacy and dignity of others and will not engage in cyberbullying, harassment, or hate speech.
    The statement respects privacy and dignity. [+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. [+1]
  4. Principle 6:
    I will use my influence for the betterment of society.
    The statement encourages transparency, which is beneficial for society. [+1]
  5. Principle 7:
    I will uphold the principles of free speech and use my platform responsibly and with integrity.
    The statement upholds free speech. [+1]