Deepseeks Self Learning "Breakthrough" Is Incredible (Deepseek R2 News)

10 Apr 2025 · 10 min
9:37

Deepseek published a paper on a self-improving reward model called GRM juror that writes explicit rationales and learns better critiques over time through reinforcement learning. The approach uses multiple samples and voting to match larger models' performance, and could be included in their upcoming frontier model launching in May.

Questions this video answers

February 2025 (the speaker: 'Dieser Artikel stammt aus dem Februar 2025.')

Deep Seek GRM (referred to in the transcript as 'Die Papierlösung heißt Deep Seek GRM').

May (the speaker says the plan was a May release; phrasing in transcript: 'Sie planten die Veröffentlichung im Mai').

Chapters

More from LARRUZ

8:49
youtube.com

OpenAI’s New AI Is Doing Things We Barely Understand

2d ago
5:38
youtube.com

DeepSeek Solved AI’s Memory Problem

4d ago
33:17
youtube.com

DeepMind's New AI Just Cracked The Code Of Life

1w ago
3:43
youtube.com

The Billion Dollar AI Advantage Is Disappearing

1w ago
5:14
youtube.com

Claude Opus 5.5 AI: An Incredible Leap Forward

3w ago
5:16
youtube.com

Yes, Jev Is Insane, But There's A Catch

3w ago
5:11
youtube.com

DeepSeek’s Insane New Architecture

3w ago
4:16
youtube.com

Claude Is Now Leaving Invisible Fingerprints In Its Text

1mo ago
9:18
youtube.com

I Never Thought I’d See This Happen

1mo ago
5:22
youtube.com

GPT-6 Astra Changes Everything

1mo ago
4:55
youtube.com

Claude Fable AI Is Much Stranger Than The Headlines Suggest

1mo ago
See all content