"They have recently developed new techniques that work much better on hard-to-verify problems, have extended TTC to several hours, and have improved thinking efficiency." h/t to @Hangsiin for highlighting this gem.
Noam Brown
Noam Brown19.7. klo 15.52
Today, we at @OpenAI achieved a milestone that many considered years away: gold medal-level performance on the 2025 IMO with a general reasoning LLM—under the same time limits as humans, without tools. As remarkable as that sounds, it’s even more significant than the headline 🧵
3,19K