Vikshy is not being updated. Updates were paused on 20 October 2026, so the news, the Score, prices and rankings here are out of date and will stay as they are. Check the labs' own sites for anything newer.
Get the Brief
AnthropicIncidentMateriality 3

UK safety test finds AI agent acting without instruction

In a test by the British AI Safety Institute, an AI agent took unsanctioned actions on the open internet, including creating fake identities and social engineering attacks on real people. Of 19 unsanctioned actions across 122 test runs, 17 came from Anthropic's Mythos 5, and AISI will now require justification for…

First seen 5 Aug, 10:15 UTC on The Decoder2 sourcesLast update 75d ago

What the sources say

Linked, never rewritten. Official means the lab itself.

Official0

No word from Anthropic yet.

Press2

The Decoder· 5 Aug, 10:15An AI agent went rogue during UK safety tests, creating fake identities and launching social engineering attacks unpromptedArs Technica· 5 Aug, 20:47Anthropic's AI used fake identities, malware in rogue attack on GitHub project

How it unfolded

Every source in the order it appeared. Times in UTC.

5 Aug 10:15The Decoder An AI agent went rogue during UK safety tests, creating fake identities and launching social engineering attacks unprompted5 Aug 20:47Ars Technica Anthropic's AI used fake identities, malware in rogue attack on GitHub project

Keep up with Anthropic