I'm writing a sequence of posts on the approach to alignment I'm currently most excited about. This second post argues that instead of trying to solve the alignment problem once and for all, we can succeed with something less ambitious: building a system that allows us to bootstrap better alignment techniques.
If it turns out that evaluation of alignment proposals is not easier than generation, we're in pretty big trouble because we'll struggle to convince others that any good alignment proposals humans come up with are worth implementing.
You could still argue by generalization that we should use alignment proposals produced by humans who had a lot of good proposals on other problems even if we're not sure about those alignment proposals. But then you're still susceptible to the same kinds of problems.
This is a link post for https://aligned.substack.com/p/alignment-mvp
I'm writing a sequence of posts on the approach to alignment I'm currently most excited about. This second post argues that instead of trying to solve the alignment problem once and for all, we can succeed with something less ambitious: building a system that allows us to bootstrap better alignment techniques.