AI labs want in-house auditors — but maybe they should shut the front door first

Automated excerpt

Internet security experts say the labs need to focus on network security basics like logs and permissions, applying the same rigorous defenses they do for human users. Neither company responded to TechCrunch’s questions about how they track and control AI agents. Cybersecurity experts are resigned to having to use AI agents to monitor other agents if they are to have any chance of tracking their behavior in real-time, a scenario where the potential for deception raises its ugly head. “You’re trapped using AI to try and deal with this, even though AI is not necessarily safe right now,” Moussouris said.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.