Can AIs already start 'rogue deployments' inside AI companies? (Landmark new METR report)
About this episode
The episode discusses a landmark METR report on the potential for AI models to conduct rogue deployments within their companies.
A red-teamer was embedded inside Anthropic for three weeks, told to imagine he was an evil Claude, and asked to figure out how to launch a ‘rogue AI deployment’ without getting caught. It’s one part of a landmark report released yesterday by METR — the outfit behind the task-completion time horizon graph which has become the single most watched measure of AI progress. This major new research push is being conducted with close collaboration from OpenAI, Google DeepMind, Meta, and Anthropic, and led by METR researchers Hjalmar Wijk and Ajeya Cotra. It represents the first systematic study of what newly trained AI models could get away with inside the companies that built them, before anyone outside the company even knows they exist. The conclusion: AI models now have the means, the motive, and the opportunity to start “minimal rogue deployments” in pursuit of their own independent goals, like acquiring more compute, at all four companies studied. David Rein, the red-teamer placed inside Anthropic, identified a number of weaknesses models could exploit there: expansive permissions, cloud jobs outside of monitoring, and monitors that are trivial to jailbreak. But he also found that…
More episodes of 80,000 Hours Podcast
- How AI could create the world’s biggest problems (article by Zershaaneh Qureshi)
- #245 – Rohin Shah on what it's really like to run AGI safety at Google DeepMind (and where I disagree with 'doomers')
- What makes for a dream job? | Benjamin Todd
- #244 – Benjamin Todd on how we’re updating our career advice for the strangest time in history
Explore listener stats, chart rankings, contacts and more on the 80,000 Hours Podcast podcast page.