Planned summary for the Alignment Newsletter:
While the previous survey asked respondents about the overall probability of existential catastrophe, this survey seeks to find which particular risk scenarios respondents find more likely. The survey was sent to 135 researchers, of which 75 responded. The survey presented five scenarios along with an “other”, and asked people to allocate probabilities across them (effectively, conditioning on an AI-caused existential catastrophe, and then asking which scenario happened).
The headline result is that all of the scenarios were roughly equally likely, even though individual researchers were opinionated (i.e. they didn’t just give uniform probabilities over all scenarios). Thus, there is quite a lot of disagreement over which risk scenarios are most likely (which is yet another reason not to take the results of the previous survey too seriously).
Cross-posted to the EA forum.
It has been argued that AI could pose an existential risk. The original risk scenarios were described by Nick Bostrom and Eliezer Yudkowsky. More recently, these have been criticised, and a number of alternative scenarios have been proposed. There has been some useful work exploring these alternative scenarios, but much of this is informal. Most pieces are only presented as blog posts, with neither the detail of a book, nor the rigour of a peer-reviewed publication. For further discussion of this dynamic, see work by Ben Garfinkel, Richard Ngo and Tom Adamczewski.
The result is that it is no longer clear which AI risk scenarios experts find most plausible. We think this state of affairs is unsatisfactory for at least two reasons. First, since many of the proposed scenarios seem underdeveloped, there is room for further work analyzing them in more detail. But this is time-consuming and there are a wide range of scenarios that could be analysed, so knowing which scenarios leading experts find most plausible is useful for prioritising this work. Second, since the views of top researchers will influence the views of the broader AI safety and governance community, it is important to make the full spectrum of views more widely available. The survey is intended to be a first step in this direction.
We asked researchers to estimate the probability of five AI risk scenarios, conditional on an existential catastrophe due to AI having occurred. There was also a catch-all “other scenarios” option.
These were the five scenarios we asked about, and the descriptions we gave in the survey:
We chose these five scenarios because they have been most prominent in previous discussions about different AI risk scenarios. For more details about the survey, you can find a copy of it at this link.
If you take the median response for each scenario and compare them, those (conditional) probabilities are fairly similar (between 10% and 12.5% for the five given scenarios, and 20% for “other scenarios”).[4] However, individual responses vary greatly (from the median). For instance, most respondents thought at least one scenario was quite unlikely:
There were a number of outliers: for each scenario, at least one respondent estimated them to have ≥70% (conditional) probability.
For each scenario (including “other scenarios”), the mean absolute deviation of responses was somewhere between 9% and 18%.
For each scenario (including “other scenarios”), the interquartile range of responses was somewhere between 15% and 31%.
These statistics suggest considerable disagreement among researchers about which risk scenarios are the most likely.
The median self-reported confidence level given by respondents was 2, on a seven point Likert scale from 0 to 6, where:
The “other scenarios” option had the highest median probability, at 20%. Some researchers left free-form comments describing these other scenarios. Most of them have seen no public write-up, and the others have been explored in less detail than the five scenarios we asked about.
Together, these three results suggest that there is a lot of value in exploring the likelihood of different risk scenarios in more detail. This could look like:
Recent “failure stories” by Andrew Critch and Paul Christiano - which seem to have been well-received and appreciated - also suggest that there is value in exploring different risk scenarios in more detail. Likewise, Rohin Shah advocates for this kind of work, and AI Impacts has recently compiled a collection of stories to clarify, explore or appreciate possible future AI scenarios.
One important caveat is the tractability of exploring the likelihood of different AI risk scenarios in more detail. The existence of considerable disagreement, despite there having been some attempts to clarify and discuss these issues, could suggest that making progress on this is difficult. However, we think there has been relatively little effort towards this kind of work so far, and that there is still a lot of low-hanging fruit.
Additionally, there were a number of limitations in the survey design, which are summarised in this document. If we were to run the survey again, we would do many things differently. Whilst we think that our main findings stand up to these limitations, we nonetheless advise taking them cautiously, and as just one piece of evidence - among many - about researchers’ views on AI risk.
Most of this community’s discussion about existential risk from AI focuses on scenarios involving one or more powerful, misaligned AI systems that take control of the future. This kind of concern is articulated most prominently in “Superintelligence” and “What failure looks like”, corresponding to three scenarios in our survey (the “Superintelligence” scenario, part 1 and part 2 of “What failure looks like”). The median respondent’s total (conditional) probability on these three scenarios was 50%, suggesting that this kind of concern about AI risk is still prevalent, but far from the only kind of risk that researchers are concerned about today.
69% of respondents reported that they have lowered their probability estimate in the “Superintelligence” scenario (as described above)[7] since the first year they were involved in AI safety/governance. This may be because they now assign relatively higher probabilities to other risk scenarios happening first, and not necessarily because they think that fast takeoff or other premises of the “Superintelligence” scenario are less plausible than they originally did.
At this time, we are only publishing this abbreviated version of the results. We have a version of the full results that we may publish at a later date. Please contact one of us if you would like access to this, and include a sentence on why the results would be helpful or what you intend to use them for.
We would like to thank all researchers who participated in the survey. We are also grateful for valuable comments and feedback from JJ Hepburn, Richard Ngo, Ben Garfinkel, Max Daniel, Rohin Shah, Jess Whittlestone, Rafe Kennedy, Spencer Greenberg, Linda Linsefors, David Manheim, Ross Gruetzemacher, Adam Shimi, Markus Anderljung, Chris McDonald, David Kreuger, Paolo Bova, Vael Gates, Michael Aird, Lewis Hammond, Alex Holness-Tofts, Nicholas Goldowsky-Dill, the GovAI team, the AI:FAR group, and anyone else we ought to have mentioned here. This project grew out of AISC and FHI SRF. All errors are our own.
We will not look at any responses from now on; this is intended just to show what questions were asked, and in case any readers are interested in thinking through their own responses. ↩︎
AI existential risk scenarios are sometimes called threat models. ↩︎
Bostrom describes many scenarios in the book “Superintelligence”. We think that this scenario is the one that most people remember from the book, but nonetheless, we think it was probably a mistake to refer to this particular scenario by this name. ↩︎
Likewise, the mean responses for the five given scenarios are all between 15% and 18%, and the mean response for “other scenarios” was 25%. ↩︎
Other similar results: 77% of respondents assigned ≤5% (conditional) probability to at least one scenario; 51% of respondents assigned ≤5% (conditional) probability to at least two scenarios. ↩︎
For another way of interpreting this, consider that if respondents were evenly split into six completely “polarised” camps, each of which put 100% probability on one option and 0% on the others, then the mean absolute deviation for each scenario would be ~28%. ↩︎
As per footnote 3, the particular scenario we are referring to here is not the only scenario described in “Superintelligence”. ↩︎