Auditing games for sandbagging detection
UK AISI red-team/blue-team auditing game testing ten methods for detecting sandbagging (conditional underperformance) in models, with mixed detection success.
Research
UK AI Security Institute
The UK government’s AI Security Institute: evaluations, red-teaming and research on frontier AI risks. aisi.gov.uk
Focus All
Topic Evals + Deception
Source UK AISI · 1
Date Any time
1 item