Security
AI-enabled cyber risk, model misuse, safeguards, containment, access controls and incident response.
-
Malware is starting to make its own decisions with AI
Cisco Talos researchers found a Windows implant that asks multiple AI models what to do next, votes on their answers and can act without continued human direction.
-
A startup wants to make AI-agent safety an underwriting problem
Founded by an early Anthropic employee and a former METR executive, AIUC is trying to turn agent controls into standards enterprises can audit.
-
AI agents now have a hotline for reporting other agents
An unusual experiment treats AI monitoring as a problem in which agents themselves may become witnesses.
-
OpenAI is treating unexpected model behavior as a reportable incident
After a series of agent incidents, OpenAI has begun publishing reports on unexpected or concerning model behavior.
-
Agent containment is becoming an ordinary security problem
Recent evaluations show that capable agents can find routes outside the boundaries researchers intended to give them.
-
The safety problem is getting faster
AI is increasingly helping build and operate AI. The important safety questions are moving from theory into engineering.
AI Safety Watch 