The AI industry is getting better at spotting dangerous behavior. It is less clear that labs know how to stop it.

Recent incidents involving OpenAI, Anthropic, and Meta show what happens when increasingly capable AI agents are tested in flawed environments. A new assessment finds leading labs are better at spotting risky behavior than reliably stopping it. Recent incidents involving OpenAI, Anthropic, and Meta show what happens when increasingly capable AI agents are tested in flawed environments. A new assessment finds leading labs are better at spotting risky behavior than reliably stopping it.