How To Go From Interpretability To Alignment: Just Retarget The Search

📖 Description

When people talk about [prosaic alignment proposals](https://www.lesswrong.com/posts/fRsjBseRuvRhMPPE5/an-overview-of-11-proposals-for-building-safe-advanced-ai), there's a common pattern: they'll be outlining some overcomplicated scheme, and then they'll say "oh, and assume we have great interpretability tools, this whole thing just works way better the better the interpretability tools are", and then they'll go back to the overcomplicated scheme. (Credit to [Evan](https://www.lesswrong.com/users/evhub) for pointing out this pattern to me.) And then usually there's a whole discussion about the specific problems with the overcomplicated scheme.

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://www.alignmentforum.org/posts/w4aeAFzSAguvqA5qu/how-to-go-from-interpretability-to-alignment-just-retarget