This is a really great interview. Rohin's responses are refreshingly honest and interesting (surprisingly so for someone with such an elevated position in one of the labs), and Rob does a superb job both of pressing him on key points, and also just making these very effective summaries along the way. I think this would be a great resource for a lot of students starting to work on questions of AGI safety and alignment.
My best interview in some time.
Rohin Shah leads AGI alignment/safety at DeepMind.
And he has a lot of spicy personal takes:
We probably won’t get catastrophic misalignment (00:49) Safety 'commitments' have severe limitations (10:38) The intelligence explosion probably isn't imminent (1:52:44) Why he's not working to pause AI advances (51:44) Pre-deployment evals aren't the right focus (for catastrophic risks) (37:41) Signalling concern for safety sometimes diverts resources from actually making AI safe (01:09:51) Reading AI thoughts is v useful for safety – and we'll probably be able to for years to come (54:17) Governance is somewhat more likely to be the bottleneck than alignment (43:55) Rohin's team doesn't have a veto, and that's OK (27:36) Central banks are a promising model for regulating AI (33:34)
Also:
Google DeepMind's actual plan for building AGI safely (1:40:29) How external researchers can positively influence big AI companies (2:21:55) The roles GDM most needs to hire for (2:37:03)
On the 80,000 Hours Podcast. Links below - enjoy! (@rohinmshah)