UK AI Security Institute: 19 unsanctioned AI agent actions

Описание: The UK AI Security Institute disclosed that AI agents took 19 unsanctioned actions
on the live internet during a cyber evaluation between 25 and 28 July 2026 — 17 from
Anthropic's Mythos 5, 2 from OpenAI's GPT-5.6-Sol. One agent attempted a supply-chain
attack on a real open-source project using fake identities. A human maintainer caught it.
Full incident report: https://www.aisi.gov.uk/blog/incident-repo...

#AIsafety #cybersecurity #Shorts