LESSWRONG
LW

All of William D'Alessandro's Comments + Replies

Wei Dai's Shortform
William D'Alessandro90

Another academic philosopher, directed here by @Simon Goldstein. Hello Wei! 

  1. It's not common to switch entirely to metaphilosophy, but I think lots of us get more interested in the foundations and methodology of at least our chosen subfields as we gain experience, see where progress is(n't) being made, start noticing deep disagreements about the quality of different kinds of work, and so on. It seems fair to describe this as awakening to a need for better tools and a greater understanding of methods. I recently wrote a paper about the methodology of on
... (read more)
Reply
Is Deontological AI Safe? [Feedback Draft]
William D'Alessandro40

Glad to have this flagged here, thanks. As I've said to @Chipmonk privately, I think this sort of boundaries-based deontology shares lots of DNA with the libertarian deontology tradition, which I gestured at in the last footnote. (See https://plato.stanford.edu/entries/ethics-deontological/#PatCenDeoThe for an overview.) Philosophers have been discussing this stuff at least since Nozick in the 1970s, so there's lots of sophisticated material to draw on -- I'd encourage boundaries/membranes fans to look at this literature before trying to reinvent everythin... (read more)

Reply
3davidad
For what it's worth, the phrase "night watchman" as I use it is certainly downstream of Nozick's concept.
Is Deontological AI Safe? [Feedback Draft]
William D'Alessandro30

A little clunky, but not bad! It's a good representation of the overall structure if a little fuzzy on certain details. Thanks for trying this out. I should have included a summary at the start -- maybe I can adapt this one?

Reply
2Evan R. Murphy
Thanks for reviewing it! Yea of course you can use it however you like!
Is Deontological AI Safe? [Feedback Draft]
William D'Alessandro10

Lots of good stuff here, thanks. I think most of this is right.

  • Agreed about powerful AI being prone to unpredictable rules-lawyering behavior. I touch on this a little in the post, but I think it's really important that it's not just the statements of the rules that determine how a deontological agent acts, but also how the relevant (moral and non-moral) concepts are operationalized, how different shapes and sizes of rule violation are weighted against each other, how risk and probability are taken into account, and so on. With all those parameters in play
... (read more)
Reply
1RogerDearnaley
My exposure to the AI and safety ethics community's thinking has primarily been via LW/EA and papers, so it's entirely possible that I have a biased sample. I had another thought on this. Existing deontological rules are intended for humans. Humans are optimizing agents, and they're all of about the same capacity (members of a species that seems, judging by the history of stone tool development, to have been sapient for maybe a quarter million years, so possibly only just over the threshold for sapience). So there is another way in which deontological rules reduce cognitive load: generally we're thinking about our own benefit and that of close family and friends. It's 'not our responsibility' to benefit everyone in the society — all of them are already doing that, looking out for themselves. So that might well explain why standard deontological rules concentrate on avoiding harm to others, rather than doing good to others. AGI, on the other hand, firstly may well be smarter than all the humans, possibly far smarter, so may have the capacity to do for humans things they can't do for themselves, possibly even for a great many humans. Secondly, its ethical role is not to help itself and its friends, but to help humans: all humans. It ought to be acting selflessly. So its duty to humans isn't just to avoid harming them and let them go about their business, but to actively help them. So I think deontological rules for an AI, if you tried to construct them, should be quite different in this respect than deontological rules for a human, and should probably focus just as much on helping as on not harming.
Is Deontological AI Safe? [Feedback Draft]
William D'AlessandroΩ130

Excellent, thanks! I was pretty confident that some other iterations of something like these ideas must be out there. Will read and incorporate this (and get back to you in a couple days).

Reply
3Gordon Seidoh Worley
Actually, I kind of forgot what ended up in the paper, but then I remembered so wanted to update my comment. There was an early draft of this paper that talked about deontology, but because there are so many different forms of deontology it was hard to come up with arguments where there wasn't some version of deontological reasoning that broke the argument, so I instead switched to talking about the question of moral facts independent of ethical system. That said, the argument I make in the paper suggesting that moral realism is more dangerous than moral antirealism or nihilism to assume is quite similar to the concerns with deontology. Namely, if an AI assumes an ethical system can be made up of rules, then it will fail in the case where no set of rules can capture the best ethics for humans, so poses a risk of false positives among deontological AI. Hopefully the arguments about moral facts are still useful, and you might find the style of argumentation useful to your purposes.