factual
RL on LLMs now achieves expert reliability with clean feedback
The biggest change in the last year is that RL in language models has finally worked: there is now proof of an algorithm that delivers expert human reliability and performance given the right feedback loop, conclusively demonstrated so far in competitive programming and math.
factualpending
Speaker
Sholto DouglasEvidence Quote
“the biggest thing that's changed is that RL in language models has finally worked. We finally have proof of an algorithm that can give us expert human reliability and performance, given the right feedback loop.”
Created: 6/13/2026, 3:28:51 AM
Your notes
Loading notes...