Transcripts of interviews with AI researchers

post by Vael Gates · 2022-05-09T06:03:09.561Z · EA · GW · 10 comments

Contents

  Overview
  Personal notes 
None
10 comments

tldr: I conducted a series of interviews with 11 AI reseachers to discuss AI safety, which are located here: TRANSCRIPTION LINK. If you are interested in doing outreach with AI researchers, I highly recommend taking a look!

[Cross-posted to LessWrong [LW · GW].]


Overview

I recently conducted a series of interviews with 11 AI researchers, wherein I laid out some reasons to be concerned about long-term risks from AI.

These semi-structured interviews were 40-60 minutes long and conducted on Zoom. Interviewees were cold-emailed, were paid for their participation, and agreed that I may share their anonymized transcripts.

Six of the interviews were with researchers who had papers accepted at NeurIPS or ICML in 2021. Five of the interviews were with researchers who were informally categorized as “particularly useful to talk to about their opinions about safety” (generally more senior researchers at specific organizations).  

I’m attaching the raw transcripts from these 11 interviews, at the following link. I’ve also included the approximate script I was following, post-interview resources I sent to interviews, and informal interview notes in the associated “README” doc. Ideally I’d have some analysis too, and hopefully will in the future. However, I think it’s useful— particularly for people who plan to start similar projects— to read through a couple of these interviews, to get an intuitive feel for what conversations with established AI researchers can feel like.

Note: I also interviewed 86 researchers for a more complete academic, under-IRB study (whose transcripts won’t be released publicly), whose results will be posted about separately on LessWrong once I finish analyzing the data. There will be substantially more analysis and details in that release; this is just to get some transcripts out quickly. As such, I won't be replying to a lot of requests for details here.

Thanks to Sam Huang, Angelica Belo, and Kitt Morjanova, who helped clean up the transcripts! 


Personal notes 


                                                                   TRANSCRIPTION LINK

10 comments

Comments sorted by top scores.

comment by Owen Cotton-Barratt (Owen_Cotton-Barratt) · 2022-05-10T11:14:41.403Z · EA(p) · GW(p)

Thanks, I think this is really valuable.

comment by hb574 (Herbie Bradley) · 2022-05-09T15:22:11.978Z · EA(p) · GW(p)

This is great work, I think it's really valuable to get a better sense of what AI researchers think of AI safety.

Often when I ask people in AI safety what they think AI researchers think of AGI and alignment arguments, they don't have a clear idea and just default to some variation on "I'm not sure they've thought about it much". Yet as these transcripts show, many AI researchers are well aware of AI risk arguments (in my anecdotal experience, many have read at least part of Superintelligence ) and have more nuanced views. So I'm worried that AI safety is insular w.r.t mainstream AI researchers thought on AGI - and these are people who in many cases have spent their working life thinking about AGI, so their thoughts are highly valuable, and this work goes some way to reversing that insularity.

A nice followup direction to take this would be to get a list of common arguments used by AI researchers to be less worried about AI safety (or about working on capabilities, which is separate), counterarguments, and possible counter-counter arguments. Do you plan to touch on this kind of thing in your further work with the 86 researchers?

Replies from: Vael Gates
comment by Vael Gates · 2022-05-09T22:04:10.779Z · EA(p) · GW(p)

Indeed! I've actually found that in most of my interviews people haven't thought about the 50+ year future much or heard of AI alignment, given that my large sample is researchers who had papers at NeurIPS or ICML. (The five researchers who were individually selected here had thought about AI alignment uncommonly much, which didn't particularly surprise me given how they were selected.)

A nice followup direction to take this would be to get a list of common arguments used by AI researchers to be less worried about AI safety (or about working on capabilities, which is separate), counterarguments, and possible counter-counter arguments. Do you plan to touch on this kind of thing in your further work with the 86 researchers?

Yes. With the note that the arguments brought forth are generally less carefully thought-through than the ones shown in the individually-selected-population, due to the larger population. But you can get a sense for some of the types of arguments in the six transcripts from NeurIPS / ICML researchers, though I wouldn't say it's fully representative.
 

comment by Jamie Bernardi (j_bernardi) · 2022-05-17T12:35:28.131Z · EA(p) · GW(p)

I am currently pursuing a couple of projects that are intended to appeal to the sensibilities of AI researchers who aren't in the alignment community already. This has already been very useful for informing the communications and messaging I would use for those. I can see myself referring back to this often, when pursuing other field building activities too. Thanks a lot for publishing this!

comment by Vael Gates · 2022-05-18T03:16:43.202Z · EA(p) · GW(p)

I've been finding "A Bird's Eye View of the ML Field [Pragmatic AI Safety #2] [AF · GW]" to have a lot of content that would likely be interesting to the audience reading these transcripts. For example, the incentives section [AF(p) · GW(p)] rhymes with the type of things interviewees would sometimes say. I think the post generally captures and analyzes a lot of the flavor / contextualizes what it was like to talk to researchers.

comment by Ezra Newman · 2022-05-11T04:14:15.554Z · EA(p) · GW(p)

With all the “AI psychology” posts on here and Twitter, I thought this was going to be “interviews with AIs that are researchers” not “interviews with humans researching AI”. This is probably more valuable!

comment by jacquesthibs (jaythibs) · 2022-05-09T17:30:13.723Z · EA(p) · GW(p)

Fantastic work. And thank you for transcribing!

comment by NunoSempere · 2022-05-23T21:58:34.058Z · EA(p) · GW(p)

I would find this a bit more readable if you compiled everything into one big pdf.

comment by Ben_West · 2022-05-12T00:34:05.161Z · EA(p) · GW(p)

Thanks for doing this! The interviews are really interesting to read; the CEO example seems like something which perhaps should gain more prominence as a way to introduce AI-knowledgeable audiences to risks about alignment.

comment by Peter S. Park · 2022-05-11T20:02:59.184Z · EA(p) · GW(p)

This is such an incredibly useful resource, Vael! Thank you so much for your hard work on this project.

I really hope this project continues to go strong!