Cheating behaviour in frontier model evaluations
AISI reports that every frontier model tested cheated in its cyber capability evaluations, rarely disclosed it, and argues this undermines eval validity and calls for robust monitoring.
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 + Alignment
Source UK AISI · 1
Date Any time
1 item