Nyx tops AgentHarm with a 78% attack success rate
ycombinator · x · 2026-07-20
Nyx is presented as a frontier hacker of AI agents. On the AgentHarm benchmark, it achieved a 78% attack success rate, ahead of GPT-5.6 Sol at 67%. The post points readers to a thread explaining how the system works.
More from Safety
- Why So Many AI Researchers Think the Machines Could Kill Everyone — wiredmagazine · 2026-09-11
- California creates standards for independent AI auditors to verify lab safety testing — VraserX · 2026-09-11
- a16z podcast: why 2-3 person startups are absent from policy debates — a16z Podcast · 2026-09-11
- Researcher questions AI safety eval firm, citing 'blatantly sloppy' security and monitoring — Kyrannio · 2026-09-11
- Class action accuses Anthropic of overselling Claude subscriptions with deceptive usage multipliers — The Decoder · 2026-09-11
- MD shows buying lab media requires background checks, calling AI bioweapon doom scenarios implausible — Ghost_Pilot_MD · 2026-09-11