Lunjun Zhang (@lunjunzhang) 's Twitter Profile
Lunjun Zhang

@lunjunzhang

CS PhD student @UofT. Ex-intern @GoogleDeepMind. Working on LLM self-improvement. Previously worked on self-driving.

ID: 1301919425029963777

linkhttps://lunjunzhang.github.io/ calendar_today04-09-2020 16:26:06

197 Tweet

874 Takipçi

533 Takip Edilen

Lunjun Zhang (@lunjunzhang) 's Twitter Profile Photo

In retrospect, OpenAI's 'let's verify step by step' paper was a psy op. It distracted the field with PRM and MCTS—both of which were dead ends. The test-time scaling plot from O1 was also a psy op. Think about how bad 20% AIME is; the plot likely didn’t use the same checkpoint.