Learning the smooth prior

📖 Description

*Most of this document is composed of thoughts from Geoffrey Irving (safety researcher at DeepMind) written on January 15th, 2021 on [Learning the Prior](https://www.alignmentforum.org/posts/SL9mKhgdmDKXmxwE4/learning-the-prior)/[Imitative Generalization](https://www.alignmentforum.org/posts/JKj5Krff5oKMb8TjT/imitative-generalisation-aka-learning-the-prior-1), [cross-examination](https://www.alignmentforum.org/posts/Br4xDbYu4Frwrb64a/writeup-progress-on-ai-safety-via-debate-1), and [AI safety via debate](https://arxiv.org/abs/1805.00899), plus some discussion between Geoffrey and Rohin and some extra commentary from me at the end. - Evan*

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://www.alignmentforum.org/posts/9x5mtYjHYfr4T7KLj/learning-the-smooth-prior