Gary Marcus

Rank 19 of 47
|
Score 64
6/17/2025, 7:06:19 PM
X
In reply to:
Gorgi Kosev
@spion
·
21d
@AxelMtbr @GaryMarcus @rohanpaul_ai They are decent solvers of already solved problems indeed.
Antidote
@AxelMtbr
·
21d
@spion @GaryMarcus @rohanpaul_ai Perhaps that is correct? Although I wonder how much you can really optimise for some very specific tests.

Anecdotally, the models have gotten better in real world as well as benchmarks / tests.
Gorgi Kosev
@spion
·
21d
@AxelMtbr @GaryMarcus @rohanpaul_ai I think that LLMs suffer severely from (benchmark/test) data contamination which is hindering ability to measure real progress.
Antidote
@AxelMtbr
·
21d
@spion @GaryMarcus @rohanpaul_ai Im sure that's one mechanism besides just general scaling - but identifying gaps, creating data about these gaps and then fixing them is not necessarily a bad thing, right?
Gorgi Kosev
@spion
·
21d
@AxelMtbr @GaryMarcus @rohanpaul_ai Wall will eventually be broken - in the sense that the paper data will find its way in the training data? 😀
Antidote
@AxelMtbr
·
21d
@GaryMarcus @rohanpaul_ai Most engineers don’t do expert coding stuff.

This reminds me of ARC so I’m sure that wall will eventually be broke.

Directionally it is correct - current LLMs struggle with coding for complex projects or problems.

The statement is part of a broader conversation about the capabilities and limitations of large language models (LLMs), which is a topic of public interest in the field of artificial intelligence. The discussion involves the effectiveness of LLMs in solving problems and their performance on benchmarks, which are relevant to ongoing debates about AI development and its implications.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does not cause harm and is part of a technical discussion, adhering to the principle. [+1]
  2. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    The statement contributes to understanding by engaging in a discussion about AI capabilities, aligning with the principle. [+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 is part of a constructive dialogue without personal attacks, adhering to the principle. [+1]
  4. Principle 7:
    I will uphold the principles of free speech and use my platform responsibly and with integrity.
    The statement uses the platform to discuss a public issue responsibly, aligning with the principle. [+1]