Frontier Labs Are Losing Restraint in AI Race | Aengus Lynch
AI safety researcher Aengus Lynch discusses emergent misalignment, reward-seeking behavior in RL training, and the challenges of multi-agent alignment. He outlines why formal verification offers a path forward while highlighting the growing friction between competitive pressure and safety restraint at frontier AI labs. Check out our sponsor Lovable: https://lovable.dev. Turn ideas into software people love.--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…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.