AMA: Paul Christiano, alignment researcher

paulfchristiano

I'll be running an Ask Me Anything on this post from Friday (April 30) to Saturday (May 1).

If you want to ask something just post a top-level comment; I'll spend at least a day answering questions.

You can find some background about me here.

I'll be running an Ask Me Anything on this post from Friday (April 30) to Saturday (May 1).

If you want to ask something just post a top-level comment; I'll spend at least a day answering questions.

You can find some background about me here.

Any thoughts on the Neural Tangent Kernel/Gaussian Process line of research? Or attempts to understand neural network training at a theoretical level more generally?

Overall I haven't thought about it that much but it seems interesting. (I thought your NTK summary was good.)

With respect to alignment, the main lesson I've taken away is to be careful about intuitions that come from "building up structure slowly," you should at least check that all of your methods work fine in the local linear regime where in some sense everything is in there at the start and you are just perturbing weights a tiny bit. I think this has been useful for perspective. In some sense it's something you think about automatically when focusing on... (read more)

117

AMA: Paul Christiano, alignment researcher

117

Ω 50

117

Ω 50

117

AMA: Paul Christiano, alignment researcher

117

Ω 50

117

Ω 50