Timeline
UK AI Security Institute
UK government frontier-AI evaluation body; confirmed GPT-5.5 and Mythos both clear the 32-step autonomous attack benchmark.
7 of 7 entries (6 events, 1 interactions)
Filters
#96 May
Published Frontier AI Trends Report confirming GPT-5.5 cleared the 32-step autonomous attack chain on 6 May
AI: Jobs, Power & Money: GPT-5.5 clears 32-step attack chain; two models in five days#81 May
Published evaluation finding GPT-5.5 matched Mythos on 32-step attack chain
AI: Jobs, Power & Money: AISI: GPT-5.5 matches Mythos on 32-step attack#615 Apr
Published independent evaluation on 15 April confirming Mythos attack-chaining but refuting single-task superiority
AI: Jobs, Power & Money: AISI confirms Mythos 20-hour attack chain#614 Apr
#610 Apr
Mentioned in: BoE flags agentic AI systemic risk
AI: Jobs, Power & Money#67 Apr
Mentioned in: Anthropic drops ASL, expands Glasswing partners
AI: Jobs, Power & Money#624 Feb