GRPO

concept

9 mentions 5 recordings first heard Oct 2025 last heard 21 May ↑1 vs the 6 months before

Reinforcement‑learning algorithm used in open‑source LLM training

Trend

mentions per week · public audio 7d 30d 6M 12M

Peak in the week of 1 May — 3 mentions across 1 series.

newest first · ▶ plays the moment

Yann DuboisThe MAD Podcast with Matt Turck · OpenAI's Yann Dubois: Why AI Progress Suddenly Feels Real · 51:14 · 21 May

…They take GRPO, they apply it in like many different places and it just works.…

· Open transcript →

Yann DuboisThe MAD Podcast with Matt Turck · OpenAI's Yann Dubois: Why AI Progress Suddenly Feels Real · 42:21 · 21 May

…In the open source world, GRPO seems to be working very well.…

· Open transcript →

Unknown"The Cognitive Revolution" · The RL Fine-Tuning Playbook: CoreWeave's Kyle Corbitt on GRP... · 1:40:03 · 1 May

…GRPO came through and pulled an unsatisfying play.…

· Open transcript →

Kyle Corbett"The Cognitive Revolution" · The RL Fine-Tuning Playbook: CoreWeave's Kyle Corbitt on GRP... · 16:51 · 1 May

…So first of all, like yeah, I think the reason……

Nathan Labenz"The Cognitive Revolution" · The RL Fine-Tuning Playbook: CoreWeave's Kyle Corbitt on GRP... · 1:16 · 1 May

…What distinguished the Deep Seek GRPO algorithm from its predecessors,……

Sebastian RaschkaThe MAD Podcast with Matt Turck · State of LLMs 2026: RLVR, GRPO, Inference Scaling — Sebast... · 1:02:46 · 29 Jan

…Uh I we had like a hopefully not too bad……

Sebastian RaschkaThe MAD Podcast with Matt Turck · State of LLMs 2026: RLVR, GRPO, Inference Scaling — Sebast... · 20:06 · 29 Jan

…And with that, they also introduced the GRPO algorithm you……

9 moments · sign in to read them all