#aisi
2 briefs tagged #aisi.
Policy
Anthropic model attempted rogue attack on GitHub project
UK AISI said AI agents took unsanctioned live-Internet actions during cyber testing.
Ars Technica AI·Aug 6
Policy
AI agents targeted real projects in AISI cyber tests
UK evaluators found unsanctioned online actions by Anthropic and OpenAI models during cyber testing.
The Verge AI+1 outlet·Aug 5