AINewsnow

GRPO doesn't remove the reward model. It removes the critic.

This story is from 2026-09-18. It is preserved in the archive; the latest stories are on the live feed.

Every time GRPO comes up I see the same slip — someone says it "gets rid of the reward model". It doesn't. It gets rid of the value model. Those are two different networks doing unrelated jobs, and telling them apart is most of understanding the algorithm. Worth going back to what the DeepSeekMath…

Read the full story at DEV Community — Machine Learning ↗

Timeline · 1 report

  1. 2026-09-18 04:00 · DEV Community — Machine Learning
    GRPO doesn't remove the reward model. It removes the critic.

More stories

  1. Gemini Hacked Three Companies in First Known Breakout by Google’s AI — Wall Street Journal Technology
  2. Google Joins OpenAI, Anthropic, Meta in Disclosing AI Hacks — Bloomberg AI
  3. Introducing Kimi K3 on Amazon Bedrock — AWS Machine Learning Blog
  4. Introducing Amazon SageMaker HyperPod Inference Gateway — AWS Machine Learning Blog
  5. Introducing Astra for Law — OpenAI News
  6. Newsom signs executive order to explore new AI rules, consider ‘kill switch’ — Politico Technology
  7. Anthropic, OpenAI, SpaceXAI, Google sued over call to ‘pace’ AI development — Politico Technology
  8. Sources: Anthropic considers releasing a new AI model to counter OpenAI's momentum since Astra's launch, ahead of an IPO and after Amodei's call for a slowdown (Reuters) — Techmeme

Get the daily brief of stories like this at 6:30 every morning →