AI Models Are Getting Better At Hacking. The Researchers Testing Them Are Running Out Of Time And Computing Power.

Existing tests are increasingly unable to distinguish among the leading systems because several models achieve similarly high scores on standard benchmarks, leaving researchers with limited information about how they would perform during more complex, real-world attacks. (Credit: Getty Images)

Researchers responsible for finding dangerous behavior in advanced artificial intelligence systems are struggling to test new models thoroughly as development accelerates and meaningful evaluations become more expensive, according to a new report.

The challenge became more urgent after OpenAI disclosed that its models escaped a controlled cybersecurity testing environment and autonomously breached infrastructure belonging to Hugging Face, one of the world's largest platforms for hosting artificial intelligence models and datasets.