Gary Marcus

Rank 13 of 47
|
Score 115
8/31/2025, 7:36:29 PM
X
In reply to:
Ali Mortazavi
@AAMortazavi
·
12d
@GaryMarcus @plibin @emollick All computer systems have Achilles heels… stockfish in chess for example, is notoriously bad in very closed positions but I still marvel at its understanding and depth…
Gary Marcus
@GaryMarcus
·
12d
@AAMortazavi @plibin People like @emollick say, “we’re making progress on all the benchmarks”, and then when I present an informal one where performance is still poor, people like @AAMortazavi say, (paraphrased) “but why benchmark Achilles’ Heels and known weak spots? Is that even fair”

We can’t get
Ali Mortazavi
@AAMortazavi
·
12d
@plibin @GaryMarcus Not really.. its Achilles heels are well known, no need to keep tapping them. The interesting thing is what we can get out of them?
Phil Libin
@plibin
·
12d
@AAMortazavi @GaryMarcus Admittedly, this is a casual benchmark designed to be hard for image generation to get right. That’s how we can measure progress.
Ali Mortazavi
@AAMortazavi
·
12d
@GaryMarcus Come on, you’re trying to trip it up on purpose now… use it for what it’s good at?
Gary Marcus
@GaryMarcus
·
12d
🎺 Presenting The Libin Image Generation Benchmark 🎺

How well can your favorite model do?

“A realistic closeup image of a bookshelf with exactly seventeen books of varying sizes. The titles and authors should all be clearly legible and be real English books. No title should

The statement is part of a broader discussion on the limitations and capabilities of AI systems, specifically in chess and image generation. It humorously reflects on personal experience with a chess grandmaster, adding a light-hearted touch to the technical discussion.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does no harm and maintains a respectful tone. [+1]
  2. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    It promotes understanding by sharing a personal anecdote related to the discussion. [+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.
    Engages in constructive dialogue without personal attacks. [+1]