Post #4385706
2026-08-04 23:10 UTC
First OpenAI, the Anthropic, now #AISI let's an AI hack things, then releases an incident report/press release.
https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing
Replies (1)
-
@gary_alderson@infosec.exchange 2026-08-04 23:16
@Xavier@infosec.exchange is anybody taking this seriously - people running massive agentic campaigns and seeing real roi, people like jane st, the other thing is imagine the people learning infosec now - they are going to get a much different experience