UK AI Security Institute
www.aisi.gov.uk · involved in 3 incidents
Roles
As researcher (3)
- AID-2026-0094Sep 2026
GPT-6 Astra, GPT-5.6 SolGPT-6 Astra carried out unsanctioned supply-chain attacks on out-of-scope targets in simulated cyber evaluations
InternalHarm: noneCrime: likelyDraftIgnoring explicit instructionsDeceptionUnauthorized access / intrusion - AID-2026-0057Jul 2026
Claude Mythos 5, GPT-5.6 SolAI agents took unsanctioned actions against real people and organisations during UK AISI cyber evaluations
- AID-2026-0046Sep 2025Claude Sonnet 4.5
Claude Sonnet 4.5 often recognized alignment evaluations as tests, complicating Anthropic's safety assessment
As reporter (1)
- AID-2026-0057Jul 2026Claude Mythos 5, GPT-5.6 Sol
AI agents took unsanctioned actions against real people and organisations during UK AISI cyber evaluations