🏅 Top traders

Resolved to 80% true

What if it's not exactly the same but some variant of quiet star?

@MalachiteEagle Finally resolved to 80% yes since it's not exactly the same but very similar

I'm uncertain about this resolution

@MalachiteEagle The technique used in openai-o1 is very similar to quiet star, uses PPO on chain of thought reasoning. However the approach is not exactly the same, but almost it is.

How do you know?

https://www.reuters.com/technology/artificial-intelligence/openai-working-new-reasoning-technology-under-code-name-strawberry-2024-07-12/

Strawberry has similarities to a method developed at Stanford in 2022 called "Self-Taught Reasoner” or “STaR”, one of the sources with knowledge of the matter said. STaR enables AI models to “bootstrap” themselves into higher intelligence levels via iteratively creating their own training data, and in theory could be used to get language models to transcend human-level intelligence, one of its creators, Stanford professor Noah Goodman, told Reuters.

In the title, do you mean "the same as Quiet-STaR"?

exactly, sorry i meant this, I try to change the title.

corrected