AI ALIGNMENT FORUM
AF

Personal Blog

4

Model-free decisions

by Paul Christiano
2nd Dec 2014
1 min read
4

4

Personal Blog
Model-free decisions
0Daniel Dewey
0Daniel Dewey
0Daniel Dewey
New Comment
3 comments, sorted by
top scoring
Click to highlight new comments since: Today at 11:27 PM
[-]Daniel Dewey11y00

It seems that if it is desired, the overseer could also set their behaviour and intentions so that the approval-directed agent acts as we would want an oracle or tool to act. This is a nice feature.

Reply
[-]Daniel Dewey11y00

I think Nick Bostrom and Stuart Armstrong would also be interested in this, and might have good feedback for you.

Reply
[-]Daniel Dewey11y00

High-level feedback: this is a really interesting proposal, and looks like a promising direction to me! Most of my inline comments on Medium are more critical, but that doesn't reflect my overall assessment.

Reply
Moderation Log
Curated and popular this week
3Comments

Much concern about AI comes down to the scariness of goal-oriented behavior. A common response to such concerns is "why would we give an AI goals anyway?" I think there are good reasons to expect goal-oriented behavior, and I've been on that side of a lot of arguments. But I don't think the issue is settled, and it might be possible to get better outcomes by directly specifying what actions are good. I flesh out one possible alternative here.

(As an experiment I wrote the post on medium, so that it is easier to provide sentence-level feedback, especially feedback on writing or low-level comments. Big-picture discussion should probably stay here.)