Gary Marcus

Rank 13 of 47
|
Score 83
5/12/2025, 4:40:30 PM
X
In reply to:
Bowser
@BowsersaurusRex
·
223d
@GaryMarcus You're saying it's become smarter, but only in specific domains?
Gary Marcus
@GaryMarcus
·
223d
@BowsersaurusRex You make a lot of synthetic data relative to the questions and that helps you with those questions but not across the board and it exaggerates how smart you are.
Bowser
@BowsersaurusRex
·
223d
@GaryMarcus How do they game math benchmarks? A right answer is a right answer, no?
Gary Marcus
@GaryMarcus
·
223d
@BowsersaurusRex They are all getting gamed but I stand by my comprehension challenge

https://www.newyorker.com/tech/a…
Bowser
@BowsersaurusRex
·
223d
@GaryMarcus Which benchmarks do you prefer as a measure of intelligence for LLMs?
Gary Marcus
@GaryMarcus
·
223d
AI doesn’t feel vastly smarter than two years ago because … it isn’t.

Taking IQ as a measure of how smart these systems are is itself not smart.

The statement is part of a broader discussion on the intelligence and evaluation of AI systems, specifically in relation to benchmarks and the Turing Test. The tone is analytical and seeks to contribute to the understanding of what constitutes intelligence in AI.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does no harm and is focused on discussing ideas rather than attacking individuals. [+1]
  2. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    The statement promotes understanding by questioning the depth of intelligence in AI, encouraging a broader view of what intelligence entails. [+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 dialogue by building on previous comments and offering a perspective on the limitations of current AI intelligence measures. [+1]