Poster · Sydney
Mitigating Reward Hacking via Task Representations
- When
- Tue 8 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 1
- Authors
- Lillian Sun, Joe Benton, Eric Easley
- Organisations
- OpenAI, University of Oxford