What Happens When We Lose Control? | Aengus Lynch
Aengus Lynch joins MTS to discuss the mechanics of agentic misalignment, the challenges of evaluating AI loss of control, and how formal verification can prevent unsafe model behavior. He shares insights from recent safety evaluations and explains why internal model reasoning poses new oversight risks.
--
https://x.com/aengus_lynch1
--
MTS is a live news and interview show covering technology, business, politics, and culture as it happens.
Follow MTS:
X | https://twitter.com/MTSlive
YouTube | https://www.youtube.com/@mtsituation
Spotify |…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.