This is exemplified by John Wentworth’s viewpoint that successfully Retargeting the Search is a version of solving the outer alignment problem.
Could you explain what you mean by this? IMO successfully retargeting the search solves inner alignment but it leaves unspecified the optimization target. Deciding what to target the search at seems outer alignment-shaped to me.
Yes, I agree with that. I’ll reformulate it. What I meant is what you write: if you’re able to retarget the search in the first place, then you have no inner alignment problem anymore. Then everything is about choosing the natural abstraction in the model that corresponds to what we want, and that is an outer alignment problem.
Could you explain what you mean by this? IMO successfully retargeting the search solves inner alignment but it leaves unspecified the optimization target. Deciding what to target the search at seems outer alignment-shaped to me.
Also, nice post! I found it clear.
Yes, I agree with that. I’ll reformulate it. What I meant is what you write: if you’re able to retarget the search in the first place, then you have no inner alignment problem anymore. Then everything is about choosing the natural abstraction in the model that corresponds to what we want, and that is an outer alignment problem.