The alignment problem from a deep learning perspective

📖 Description

*This report (*[*now available on arxiv*](https://arxiv.org/abs/2209.00626)*) is intended as a concise introduction to the alignment problem for people familiar with machine learning. It translates previous arguments about misalignment into the context of deep learning by walking through an illustrative AGI training process (a framing drawn from* [*an earlier report by Ajeya Cotra*](https://www.lesswrong.com/posts/pRkFkzwKZ2zfa3R6H/without-specific-countermeasures-the-easiest-path-to)*), and outlines possible research directions for addressing different facets of the problem.*

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://www.alignmentforum.org/posts/KbyRPCAsWv5GtfrbG/the-alignment-problem-from-a-deep-learning-perspective