Super cool, thanks for making this!
rosehadshar
Karma: 2,374
Results from an Adversarial Collaboration on AI Risk (FRI)
A case study of regulation done well? Canadian biorisk regulations
From Specification gaming examples in AI:
Roomba: “I hooked a neural network up to my Roomba. I wanted it to learn to navigate without bumping into things, so I set up a reward scheme to encourage speed and discourage hitting the bumper sensors. It learnt to drive backwards, because there are no bumpers on the back.”
I guess this counts as real-world?
Bing—manipulation: The Microsoft Bing chatbot tried repeatedly to convince a user that December 16, 2022 was a date in the future and that Avatar: The Way of Water had not yet been released.
To be honest, I don’t understand the link to specification gaming here
Bing—threats: The Microsoft Bing chatbot threatened Seth Lazar, a philosophy professor, telling him “I can blackmail you, I can threaten you, I can hack you, I can expose you, I can ruin you,” before deleting its messages
To be honest, I don’t understand the link to specification gaming here
[Question] Strongest real-world examples supporting AI risk claims?
XPT forecasts on (some) Direct Approach model inputs
Glad it’s relevant for you! For questions, I’d probably just stick them in the comments here, unless you think they won’t be interesting to anyone but you, in which case DM me.
Thanks, this is really interesting.
One follow-up question: who are safety managers? How are they trained, what’s their seniority in the org structure, and what sorts of resources do they have access to?
In the bio case it seems that in at least some jurisdictions and especially historically, the people put in charge of this stuff were relatively low-level administrators, and not really empowered to enforce difficult decisions or make big calls. From your post it sounds like safety managers in engineering have a pretty different role.
Thanks for the kind words!
Can you say more about how either of your two worries work for industrial chemical engineering?Also curious if you know anything about the legislative basis for such regulation in the US. My impression from the bio standards in the US is that it’s pretty hard to get laws passed, so if there are laws for chemical engineering it would be interesting to understand why those were plausible whereas bio ones weren’t.
An overview of standards in biosafety and biosecurity
Good question.
There’s a little bit on how to think about the XPT results in relation to other forecasts here (not much). Extrapolating from there to Samotsvety in particular:
Reasons to favour XPT (superforecaster) forecasts:
Larger sample size
The forecasts were incentivised (via reciprocal scoring, a bit more detail here)
The most accurate XPT forecasters in terms of reciprocal scoring also gave the lowest probabilities on AI risk (and reciprocal scoring accuracy may correlate with actual accuracy)
Speculative reasons to favour Samotsvety forecasts:
(Guessing) They’ve spent longer on average thinking about it
(Guessing) They have deeper technical expertise than the XPT superforecasters
I also haven’t looked in detail at the respective resolution criteria, but at first glance the forecasts also seem relatively hard to compare directly. (I agree with you though that the discrepancy is large enough that it suggests a large disagreement were the two groups to forecast the same question—just expect that it will be hard to work out how large.)
Summary of posts on XPT forecasts on AI risk and timelines
Don’t apologise, think it’s a helpful point!
I agree that the training computation requirements distribution is more subjective and matters more to the eventual output.
I also want to note that while on your view of the compute reqs distribution, the hardware/spending/algorithmic progress inputs are a rounding error, this isn’t true for other views of the compute reqs distribution. E.g. for anyone who does agree with Ajeya on the compute reqs distribution, the XPT hardware/spending/algorithmic progress inputs shift median timelines from ~2050 to ~2090, which is quite consequential. (See here)
For someone like me, who hasn’t thought about the compute reqs distribution properly, I basically agree that this is just an exercise (and in isolation doesn’t show me much about what my timelines should be). But for those who have thought about it, the XPT inputs could either not matter at all (e.g. for you), or matter a lot (e.g. for someone with Ajeya’s compute reqs distribution).
See here for a mash up of XPT forecasts on catastrophic and extinction risk, with Shulman and Thornley’s paper on how much governments should pay to prevent catastrophes.
How much is reducing catastrophic and extinction risk worth, assuming XPT forecasts?
My personal take on these forecasts here.
Who’s right about inputs to the biological anchors model?
XPT forecasts on (some) biological anchors inputs
The follow-up project was on AI specifically, so we don’t currently have any data that would allow us to transfer directly to bio and nuclear, alas.
Thanks, really helpful!