Sharing AI progress in Chrome

Impressive vision benchmarking. If the vision model is truly as good as OpenAI's internal model at theoretical math, or does OpenAI have some “magic” that will be much harder to replicate for competitors?

Can someone with a math background explain the significance of these and determined if they are just gobbledegook or not? The ones with lean proofs could still be formulated incorrectly. What is strange is that last year I spent a lot of people used that to claim that these models are not really smart/creative etc. That copium didn't last for what, three months? These results are wild. Several individual findings are crazy good and use mostly unexplored methods (the improvement over Riemann for example)... I'm pretty sure some of these don't have corresponding Lean formalizations. Cool!