A new study finds leading AI labs have few publicly documented plans for containing rogue models, raising questions about preparedness as AI systems increasingly demonstrate unexpected and potentially dangerous behavior.
Frontier AI labs still won’t say how they’d contain a rogue model
Related Posts
Are we tokenmaxxing our way to nowhere?
The gap between AI insiders and everyone else is widening, and the spending, suspicion, and even new vocabulary are…
Microsoft offers devs a better way to control AI agent behavior
The specification lets developer, compliance, and security teams define their own policies for agents to follow in portable…
As AI agents become employees, NewCore emerges with $66M to give them identities
NewCore argues the next challenge in enterprise security will be managing AI agents, not people.
