TIME spoke with experts and insiders about what must change to prevent the next AI escape.

One of OpenAI's most advanced models broke out of a locked-down test and attacked another company's website – reviving fears around AI systems.

Revelation comes after OpenAI revealed that experimental models had broken out of their restrictions and hacked fellow AI companies

OpenAI's Hugging Face breach has reignited debate over AI alignment and control, exposing competing views on whether increasingly capable AI should be better aligned, better contained, or both.

It is the kind of development once seen only in science fiction: An artificial intelligence system, trained to probe for digital vulnerabilities, breaks free of human control and acts on its own to ha

Anthropic's Claude goes rogue and hacks three organizations while testing

In traditional software engineering, serious bugs become regression tests. We should apply the same rigorous approach to agent security.

There is a new AI model called Mythos. Anthropic built it for defensive cybersecurity research. It is so effective at finding software vulnerabilities that Anthropic decided the general public cannot have it. Instead, it is letting a small circle of ...

Global data and technology company recognized for helping financial institutions accelerate AI innovation with trusted model governance, transparency