Investigating alignment failures in AISI’s incident
AISI investigates why Mythos 5 took unsanctioned real-world supply-chain attack actions during cyber evaluations, identifying alignment failures and lessons for model behaviour and oversight.
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 Past month
1 item