Poster · Sydney
AI Control for Sandbagging on Fuzzy Tasks
- When
- Wed 9 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 4
- Authors
- Mikhail Terekhov, Caglar Gulcehre, Vivek Hebbar, Joe Benton
- Organisations
- EPFL, MATS, Redwood Research, University of Oxford
- QRS classification
- Language models