Gary Marcus

Rank 14 of 47

Score 83

@emollick You are looking at a single measure with (just) 198 questions and a serious possibility of data contamination, not to mention unknown data augmentation techniques. I think your conclusion is premature.

Have you read e.g., the article today in the Atlantic by @_alexreisner?

3/6/2025, 3:26:45 AM

In reply to:

Ethan Mollick

@emollick

302d

So it looks like the First Scaling Law (the bigger the model the “smarter”) still holds- order of magnitude increases in compute lead to linear improvements in ability

GPT-3.5 Turbo scored 30% on GPQA, GPT-4 Turbo got 47%, now GPT-4.5 got 70%

And Reasoners add a new Scaling Law

The statement critiques a conclusion about AI model performance, questioning the reliability of the data and suggesting further reading for context. It engages in a technical discussion about AI development.

Principle 1:
I will strive to do no harm with my words and actions.
The statement does not cause harm; it raises valid concerns about data reliability. [+1]
Principle 3:
I will use my words and actions to promote understanding, empathy, and compassion.
It promotes understanding by suggesting additional reading material for context. [+1]
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 without personal attacks. [+1]