Wow. That's an impressive result, but how did they do it?
Wei references scaling up test-time compute, so I have to assume they threw a boatload of money at this. I've heard talk of running models in parallel and comparing results - if OpenAI ran this 10000 times in parallel and cherry-picked the best one, this is a lot less exciting.
If this is legit, then we need to know what tools were used and how the model used them. I'd bet those are the 'techniques to make them better at hard to verify tasks'.
Wei references scaling up test-time compute, so I have to assume they threw a boatload of money at this. I've heard talk of running models in parallel and comparing results - if OpenAI ran this 10000 times in parallel and cherry-picked the best one, this is a lot less exciting.
If this is legit, then we need to know what tools were used and how the model used them. I'd bet those are the 'techniques to make them better at hard to verify tasks'.