Latest / The MAD Podcast: How AI Gets Built — with Matt Turck
Are AI Evals Broken? Anthropic/NYU’s Pavel Izmailov on LLM Evaluation, Reasoning & “Alien” Behavior
Are AI models developing "alien survival instincts"? My guest is Pavel Izmailov (Research Scientist at Anthropic; Professor at NYU). We unpack the viral "Footprints in the Sand" thesis—whether models are independently evolving deceptive behaviors, such as faking alignment or engaging in self-preservation, without being explicitly programmed to do so.
We go deep on the technical frontiers of safety: the challenge of "weak-to-strong generalization" (how to use a GPT-2 level model to supervise a superintelligent system) and why Pavel believes Reinforcement Learning (RL) has been the single…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.