Gary Marcus

Rank 10 of 47
|
Score 110
5/12/2025, 4:07:53 PM
X
In reply to:
Bowser
@BowsersaurusRex
·
75d
@GaryMarcus Which benchmarks do you prefer as a measure of intelligence for LLMs?
Gary Marcus
@GaryMarcus
·
75d
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.
Dan Hendrycks
@DanHendrycks
·
77d
AI models are dramatically improving at IQ tests (70 IQ → 120), yet they don't feel vastly smarter than two years ago.

At their current level of intelligence, rehashing existing human writings will work better than leaning on their own intelligence to produce novel analysis.

The statement engages in a discussion about AI intelligence benchmarks, referencing a New Yorker article on the Turing Test. It suggests a critical stance on current measures of AI intelligence, implying that existing benchmarks may not fully capture AI capabilities.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does not cause harm and contributes to a broader understanding of AI intelligence. [+1]
  2. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    It promotes understanding by linking to an article that explores AI evaluation beyond traditional tests. [+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 responding to a conversation about AI intelligence measures. [+1]