Gary Marcus

Rank 19 of 47
|
Score 89
4/23/2024, 7:36:12 PM
X
In reply to:
alth0u🤸
@alth0u
·
266d
@GaryMarcus @BrainSemantic how much would you bet?
Gary Marcus
@GaryMarcus
·
266d
@alth0u In agreement with @brainsemantic I would bet that we have nothing more than 200 ELO points better than GPT-4 11-06 preview on this benchmark by the end of 2024.
Semantic Brain
@BrainSemantic
·
267d
@GaryMarcus Expecting GPT-5 Elo score to go up ~100. Would be surprised if it goes up more than 200 points.
alth0u🤸
@alth0u
·
266d
@GaryMarcus do you have one? feels like there is one that just needs a bit of formalizing here
Gary Marcus
@GaryMarcus
·
266d
@alth0u it’s not a prediction per se
alth0u🤸
@alth0u
·
266d
.@GaryMarcus would you put money on this?
Gary Marcus
@GaryMarcus
·
266d
13.5 months post GPT-4:

• Models that are not as good as GPT-4 have become widespread.

• Models that are roughly as good GPT-4 have become common.

• Models that are significantly better than GPT-4 don’t exist.

If that doesn’t hint at diminishing returns and potential…

The statement is part of a broader conversation about the development and expectations of AI models, specifically discussing the potential performance improvements in future iterations compared to GPT-4. The discourse involves a series of exchanges about betting on the performance outcomes of these models, which adds a speculative and engaging layer to the discussion. The conversation is technical and focused on AI development, which is a significant topic in technology and artificial intelligence communities.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does no harm as it is a neutral engagement in a speculative discussion about AI model performance. [+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 the privacy and dignity of others, as it does not involve personal information or target any individual negatively. [+1]
  3. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    The statement promotes understanding by contributing to a discussion on AI development, which can be educational for those interested in the field. [+1]
  4. 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 and dialogue about AI model expectations without personal attacks. [+1]
  5. Principle 5:
    I will acknowledge and correct my mistakes.
    The statement acknowledges the speculative nature of the discussion by suggesting adding the bet to a prediction platform, which shows a willingness to correct or formalize opinions in a public and structured way. [+1]
  6. Principle 6:
    I will use my influence for the betterment of society.
    The statement uses its influence responsibly by fostering a discussion based on data and predictions rather than unfounded claims. [+1]
  7. Principle 7:
    I will uphold the principles of free speech and use my platform responsibly and with integrity.
    The statement upholds the principles of free speech by participating in an open and public exchange of ideas regarding AI development. [+1]