flâneur

Rohin Shah on what it's really like to run AGI safety at Google DeepMind (and where I disagree with 'doomers') | 80,000 Hours

80000hours.org · 32,721 words · saved by 1 readers

Building an artifact like Gemini is very, very difficult. The main reason being you have to produce this one thing, this single set of model weights, deployed using a single serving stack. And it has to satisfy so many constraints… There’s probably 100 such things. And it is the case that if you make one change to the process with the intent of making one of these things better — say, safety — it will have random downstream knock-on effects on other constraints that you totally did not anticipate. — Rohin Shah Most people working on AI safety think without a massive effort AI systems will probably end up with goals catastrophically different from humanity’s. Today’s guest, Rohin Shah — head of AGI Safety and Alignment at Google DeepMind, and an AI safety researcher since 2017 — disagrees. “There is no particularly compelling argument that this is the thing that happens by default,” Rohin explains. “There’s a lot of arguments that are suggestive that maybe it could happen, such that you

Rohin Shah on what it's really like to run AGI safety at Google DeepMind (and where I disagree with 'doomers') | 80,000 Hours Search for: On this page: 1 Introduction 1.1 The episode in a nutshell 2 Highlights 3 Articles, books, and other media discussed in the show 4 Transcript 4.1 Who's Rohin Shah? [00:00:00] 4.2 Why Rohin thinks we won't get catastrophic misalignment [00:00:49] 4.3 The limitations of safety and alignment commitments [00:10:38] 4.4 Does Rohin's team have veto power at Google DeepMind? [00:27:36] 4.5 Central banks as a roadmap for regulating AI [00:33:34] 4.6 H

saved by

related reading