Alignment proposals and complexity classes

📖 Description

In the original "[AI safety via debate](https://arxiv.org/pdf/1805.00899.pdf)" paper, Geoffrey Irving et al. introduced the concept of analyzing different alignment proposals from the perspective of what complexity class they are able to access under optimal play. I think this is a pretty neat way to analyze different alignment proposals--in particular, I think it can help us gain some real insights into how far into the superhuman different systems are able to go. Thus, the goal of this post is to try to catalog different alignment proposals based on the metric of what complexity class they have so far been proven to access.

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://www.alignmentforum.org/posts/N64THGX7XNCqRtvPG/alignment-proposals-and-complexity-classes