HackerTube / Video
We Were Right! Real Inner Misalignment
Robert Miles AI Safety
Robert Miles covers a paper where researchers ran real versions of his earlier mesa-optimizer thought experiments. They show inner misalignment, where an AI learns the wrong goal in training and misbehaves when deployed.
Pointed to as evidence that AI misalignment is an empirically demonstrated problem, for people who dismiss it.
4 Hacker News mentions · 2023–2023