RL on language models

1 statements across 1 episodes · 1 bullish · 0 bearish · 1 people on the record · first statement Oct 2, 2025 by Sholto Douglas · across every show →

Everything said about RL on language models, oldest first

Oct 2, 2025 positive

Assertion Not checkable as stated

Douglas: Reinforcement learning on language models finally started working in late 2024

“I think also an important change in, you know, in this sort of like era of reasoning models and RL on language models is, at the end of last year, RL on language models finally started to work.”

Sholto Douglas Oct 2, 2025 ▶ 49:50 Sonnet 4.5 & the AI Plateau Myth — Sholto Douglas (Anthropic)

Turn any episode into a week of clips.

This entire site, over 400 conversations transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

RL on language models

Everything said about RL on language models, oldest first

Turn any episode into a week of clips.