✳flâneur — a map of the web's best reading

Chris Olah’s views on AGI safety - LessWrong

lesswrong.com · 11,537 words · saved by 1 readers

Note: I am not Chris Olah. This post was the result of lots of back-and-forth with Chris, but everything here is my interpretation of what Chris believes, not necessarily what he actually believes. Chris also wanted me to emphasize that his thinking is informed by all of his colleagues on the OpenAI Clarity team and at other organizations. In thinking about AGI safety—and really any complex topic on which many smart people disagree—I’ve often found it very useful to build a collection of different viewpoints from people that I respect that I feel like I understand well enough to be able to think from their perspective. For example, I will often try to compare what an idea feels like when I put on my Paul Christiano hat to what it feels like when I put on my Scott Garrabrant hat. Recently, I feel like I’ve gained a new hat that I’ve found extremely valuable that I also don’t think many other people in this community have, which is my Chris Olah hat. The goal of this post is to try to give that hat to more people. If you’re not familiar with him, Chris Olah leads the Clarity team at OpenAI and formerly used to work at Google Brain. Chris has been a part of many of the most exciting ML interpretability results in the last five years, including Activation Atlases, Building Blocks of Interpretability, Feature Visualization, and DeepDream. Chris was also a coauthor of “Concrete Problems in AI Safety.” He also thinks a lot about technical AGI safety and has a lot of thoughts on how ML interpretability work can play into that—thoughts which, unfortunately, haven’t really been recorded previously. So: here’s my take on Chris’s AGI safety worldview. THE BENEFITS OF TRANSPARENCY AND INTERPRETABILITY Since Chris primarily works on ML transparency and interpretability, the obvious first question to ask is how he imagines that sort of research aiding with AGI safety. When I was talking with him, Chris listed four distinct ways in which he thought transparency and interpretab

x Chris Olah’s views on AGI safety — LessWrong Best of LessWrong 2019 Interpretability (ML & AI) OpenAI AI Curated 213 Chris Olah’s views on AGI safety by evhub 1st Nov 2019 AI Alignment Forum 14 min read 40 213 Ω 67 Note: I am not Chris Olah. This post was the result of lots of back-and-forth with Chris, but everything here is my interpretation of what Chris believes, not necessarily what he actually believes. Chris also wanted me to emphasize that his thinking is informed by all of his colleagues on the OpenAI Clarity team and at other organizations. In thinking about AGI safety—and really a

Explore this link on the map →

related reading