Rohin Shah recently had an interview on 80000 hours on his views on AGI Safety and his work at Google DeepMind. I'm posting the transcript below to encourage further discussion. I think the discussion is interesting though I disagree on a bunch of topics, especially on alignment difficulty and CoT monitoring.
Transcript
Who's Rohin Shah? [00:00:00]
Rob Wiblin: Today I’m speaking with Rohin Shah, who is head of AGI alignment and safety at Google DeepMind.
I suppose, Rohin, you’ve ended up, for better or worse — hopefully for better — being one of the more influential, dare I even say powerful, people to come out of the AGI alignment and safety ecosystem and school of thought.
You were generous enough to be super opinionated with me when you came on the show two years ago, and judging by the notes that you’ve sent over this week, you’re ready to be opinionated again.
Thanks so much for coming back on the show, Rohin.
Rohin Shah: Yeah, thanks a lot, Rob, and that's a very generous intro. And in the interest of being very opinionated, I do want to emphasise that these opinions are mine alone. They’re not meant to [...]
---
Outline:
(00:29) Transcript
(00:32) Who's Rohin Shah? \[00:00:00\]
(01:37) Why Rohin thinks we won't get catastrophic misalignment \[00:00:49\]
(10:24) The limitations of safety and alignment commitments \[00:10:38\]
(25:17) Does Rohin's team have veto power at Google DeepMind? \[00:27:36\]
(30:20) Central banks as a roadmap for regulating AI \[00:33:34\]
(34:06) How useful are pre-deployment evaluations of models? \[00:37:41\]
(39:14) Governance might be a bigger bottleneck than alignment \[00:43:55\]
(46:25) Why not just pause AI progress? \[00:51:44\]
(48:42) How much longer will we be able to read AIs' thoughts? \[00:54:17\]
(01:02:39) Sometimes, having to signal concern for safety diverts resources from actually making AI safer \[01:09:51\]
(01:20:13) Underrated GDM paper: Training away hidden reward hacks \[01:28:59\]
(01:30:51) Google DeepMind's actual plan for building AGI safely \[01:40:29\]
(01:41:03) Why Rohin doubts the intelligence explosion is imminent \[01:52:44\]
(02:06:19) Advice for external researchers who want to impact big AI companies \[02:21:55\]
(02:19:44) The most in-demand roles at GDM \[02:37:03\]
(02:25:03) How Rohin maintains his positivity \[02:42:55\]
---
First published:
June 4th, 2026
Source:
https://www.lesswrong.com/posts/4JJDvhb8MeBFsEHoC/rohin-shah-on-agi-safety
---
Narrated by TYPE III AUDIO.
