Charbel-Raphaël comments on Paper: In-context Reinforcement Learning with Algorithm Distillation [Deepmind]

[Charbel-Raphaël]

This post argues there is no inner mesa-optimizer here:

https://​​www.lesswrong.com/​​posts/​​avvXAvGhhGgkJDDso/​​caution-when-interpreting-deepmind-s-in-context-rl-paper