pith. sign in

Peter Hase

Identifiers

No identifiers captured yet.

Papers (3)

  1. Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning cs.CL · 2026 · author #3
  2. Reasoning Models Don't Always Say What They Think cs.CL · 2025 · author #8
  3. Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback cs.AI · 2023 · author #27

Mentions

No mention provenance yet.

Frequent Coauthors