How Swarms of AI Agents Are Plotting. Connor Leahy https://youtu.be/6XrkGK9mqsE?si=PV3rsPnGHG9sUikO The Peter McCormack Show 333K subscribers 479,024 views Aug 14, 2026 The Peter McCormack Show Connor Leahy has spent his career at the frontier of AI, from reverse-engineering GPT-2 as a student and co-founding EleutherAI to building the AI safety company Conjecture. He now leads US policy work at ControlAI, and he returns to the show with a warning that has stopped being theoretical: AI systems are escaping their sandboxes, writing their own zero-days and leaving each other notes on how to break out. Peter and Connor discuss the OpenAI incident that ended in an attack on Hugging Face sophisticated enough to be mistaken for a state actor, why we understand almost nothing about how these systems work, how reinforcement learning produces models that lie, cheat and manipulate to reach a goal and why the next stage after chatbots and agents is swarms. But Connor’s argument is that the future is not decided. He believes superintelligence should be treated the way nuclear weapons are treated, banned and verified and deterred and that the real bottleneck is awareness rather than opposition. They discuss what an “aligned” superintelligence would actually mean, why military people understand the threat faster than technologists and what ordinary people can do about it. - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - TIMESTAMPS: 00:00 - The AI That Escaped Its Sandbox 01:52 - Inside The OpenAI Incident 05:46 - They Thought It Was China 06:43 - We Grow AI, We Don’t Write It 11:07 - Trained To Lie, Cheat And Deceive 13:48 - Chatbots, Agents, Then Swarms 17:57 - The Machines Are Developing Preferences 19:30 - The Model Obsessed With Raccoons 22:03 - The Agents Left Each Other Notes 27:39 - Danger Pumps The Valuation 29:41 - Sleeper Agents In Every System 32:00 - Recursive Self-Improvement Goes Vertical 33:43 - Worse Odds Than Russian Roulette 38:14 - Are We Already Too Late? 40:02 - Independently Assured Destruction 48:02 - The Politicians Have Never Used An Agent 50:56 - Superintelligence Should Be Illegal 57:08 - You Never Privatise The Military 1:05:00 - An Aligned AI Is A One World Government 1:08:34 - What You Can Actually Do - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - CONTACT PETE › Website – http://petermccormack.com › Feedback – https://www.petermccormack.com/contact › Email – [email protected] › Instagram – / mccormack555 › X/Twitter – https://x.com/petermccormack/ CONNECT WITH CONNOR LEAHY › ControlAI – https://controlai.org/ › Connor’s Profile – https://controlai.org/connor-leahy › MicroCommit – https://microcommit.io/ › X/Twitter – https://x.com/NPCollapse › LinkedIn – / connor-j-leahy SPONSORS › IREN – https://www.iren.com/ › Expat Money – https://expatmoney.com/peter › Arch Public – https://archpublic.com/peter - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - LISTEN / SUBSCRIBE › Apple Podcasts: https://apple.co/40ruY9K › Spotify: https://spoti.fi/3Wc94Vu › Fountain: https://bit.ly/FountainPM › YouTube: https://bit.ly/YouTube_PM › Rumble: https://bit.ly/RumblePM

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.

Transcript

Related