Can AIs already start 'rogue deployments' inside AI companies? (Landmark new METR report)

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 frontier models were comically bad at key parts of the process, which means they can’t cause meaningful damage for now.

In this video, Rob Wiblin reconciles the conflicting picture and looks forward to METR’s second round of stress tests. They’ll begin in just a few months, a necessary move with AI advancing so quickly.

This episode was recorded on May 15, 2026.

Learn more, video, and full transcript: https://80k.info/metr-report

Chapters:

What could an unreleased AI get away with? – the new METR report (00:00:00)
Motive: Why grab more compute? (00:01:54)
Opportunity: YOLO mode and jailbreaks (00:05:46)
Means: Brilliant idiots in data centres (00:11:02)
We have to test unreleased models (00:15:45)
Especially if AI R&D is coming in 2028 (00:18:30)

Video and audio editing: Dominic Armstrong, Milo McGuire, Luke Monsour, and Josh Alward
Camera operator: Dominic Armstrong
Production: Elizabeth Cox, Nick Stockton, and Katy Moore

Tämä jakso on lisätty Podme-palveluun avoimen RSS-syötteen kautta eikä se ole Podmen omaa tuotantoa. Siksi jakso saattaa sisältää mainontaa.

Jaksot(348)

Owain Evans on accidentally training AI models to be evil

Researcher Owain Evans and his team discovered a ‘dial’ inside AI models that controls how evil they are. Relatively tiny tweaks to the training data resulted in AI models with broadly awful personali...

20 Elo 2h 15min

#251 – The UK's former head AI safety scientist on how to solve alignment before superintelligence arrives | Geoffrey Irving

When should governments slow the race toward superintelligence? According to Geoffrey Irving, the careful answer is sometime in the past. The useful answer is now.Geoffrey — formerly a safety research...

11 Elo 2h 2min

#250 – Toby Ord on where AGI timelines go wrong

Both Silicon Valley and the public can’t get enough of ‘AGI timelines.’ But Toby Ord, senior researcher at Oxford’s AI Governance Initiative and author of The Precipice, believes we consistently make ...

6 Elo 2h 46min

What the hell happened with AGI timelines in 2026? – Rob Wiblin

Last October, famed coder Andrej Karpathy called AI agents “slop.” Two months later he completely reversed his view, describing them as “alien tools” that are “rocking the profession.”He was far from ...

4 Elo 49min

#249 – Spencer Greenberg on staying sane while trying to save the world

If you genuinely believe that humanity could be wiped out by AI or a pandemic, what is the appropriate amount of fear to feel?“As much as possible” can seem like the only reasonable answer. If the wor...

28 Heinä 2h 9min

#248 – Jasmine Sun on what the people building AI really believe

Many AI researchers believe mass job displacement is coming — and some even think there’s a chance their technology will kill everyone. But they’re building it anyway. Writer and journalist Jasmine Su...

21 Heinä 1h 6min

#247 – Anton Leicht on how middle powers avoid losing everything in a post-AI world

In a post-AGI world, can a country without access to frontier AI even be considered sovereign anymore?Anton Leicht says once frontier AI becomes a core economic input, the countries that own it will p...

14 Heinä 1h 33min

#246 – Sneha Revanur on how a small team of activists helped pass America's landmark AI safety laws

Six years ago, aged just 15, Sneha Revanur founded the AI advocacy nonprofit Encode AI — back when AI felt like a niche issue. Now the world’s caught up with her, and she’s ready to share everything s...

8 Heinä 52min