Back in February, I attended the Bay Area EA Global as I have every year since they started having them. I didn't have a solid plan for what to do there this year, though, so I decided to volunteer. That means I only attended the sessions where I was on room duty, and otherwise spent the day having a few 1:1s when I wasn't on shift.
That's okay because, as everyone always says, the 1:1s are the best part of EA Global, and once again they were proven right.
Among the many great folks I met and friends I caught up with, I got the chance to meet Ronen Bar and learn about his idea of AI moral alignment. And when he told me about it, I was embarrassed I hadn't thought of it myself.
Simply put, moral alignment says that, rather than trying to align AI with human values, we try to explicitly align it to be a positive force for all sentient beings.
In all my years of thinking about AI alignment, I've not exactly ignored animals and other creatures both known and unknown, but I also figured they'd get brought along because humans care about them. But I have to admit, while it might come to the same outcome, it feels more authentic to say I want AI that is aligned to all beings rather than just humans because I, though I may be human, do in fact care about the wellbeing of all life and wish for all of it to flourish as it best can with the aid of future AI technology.
I think I missed articulating an idea like moral alignment because I was too close to the ideas. That is, I understood intuitively that if we succeeded in building AI aligned with human flourishing, that would necessarily mean alignment with the flourishing of all life, and in fact I've said that the goal of building aligned AI is to help life flourish, but not that AI should be aligned to all life directly. Now that we are much closer to building artificial superintelligence and need to figure out how to align it, the importance of aligning to non-human life stands out to me as a near-term priority.
For example, I can imagine us building human-aligned AI that ignores the plight of factory farmed animals, the suffering of shrimp, and the pain of bugs because lots of humans don't seem to care that much about their conditions. Such an AI would perhaps not be perfectly aligned in the ideal way we originally imagined aligned AI would be, but it would certainly be a kind of alignment with human goals, and it would be a travesty for the non-human beings it left out.
So let's not do that. Let's figure out how to align AI so that it's not just good for a few people or even all people, but so that it's good for all beings everywhere.
I think my previous messages made my stance on this reasonably clear, and at this point, I am beginning to question whether you are reading my messages or the OP with a healthy amount of good faith, or just reflexively arguing on the basis of "well, it wasn't obvious to me."
My position is pretty much the exact opposite of a "brief, vague formula" being "The Answer" - I believe we need to carefully specify our values, and build a complete ethical system that serves the flourishing of all things. That means, among other things, seriously investigating human values and moral epistemology, in order to generalize our ethics ahead of time as much as possible, filling in the side conditions and desiderata to the best of our collective ability and in significant detail. I consider whether and how well we do that to be a major factor affecting the success of alignment.
As I said previously, I care about the edge cases, and I care about the living things that would be explicitly excluded from consideration by your narrow focus on whether humanity survives. Not least because I think there are plenty of universes where your assumptions carry the day and humanity survives extinction, but at a monstrous and wholly avoidable cost. If you take the stance that we should be willing to sacrifice all other life on earth at the altar of humanity's survival, I simply disagree. That undermines any ethical system we would try to put into place, and if it came to pass, would be a Pyrrhic victory and an exceptionally heartless way for humanity to step forth onto the cosmic stage. We can do better, but we have to let go of this notion that only our extinction is a tragedy worth avoiding.
Back in February, I attended the Bay Area EA Global as I have every year since they started having them. I didn't have a solid plan for what to do there this year, though, so I decided to volunteer. That means I only attended the sessions where I was on room duty, and otherwise spent the day having a few 1:1s when I wasn't on shift.
That's okay because, as everyone always says, the 1:1s are the best part of EA Global, and once again they were proven right.
Among the many great folks I met and friends I caught up with, I got the chance to meet Ronen Bar and learn about his idea of AI moral alignment. And when he told me about it, I was embarrassed I hadn't thought of it myself.
Simply put, moral alignment says that, rather than trying to align AI with human values, we try to explicitly align it to be a positive force for all sentient beings.
In all my years of thinking about AI alignment, I've not exactly ignored animals and other creatures both known and unknown, but I also figured they'd get brought along because humans care about them. But I have to admit, while it might come to the same outcome, it feels more authentic to say I want AI that is aligned to all beings rather than just humans because I, though I may be human, do in fact care about the wellbeing of all life and wish for all of it to flourish as it best can with the aid of future AI technology.
I think I missed articulating an idea like moral alignment because I was too close to the ideas. That is, I understood intuitively that if we succeeded in building AI aligned with human flourishing, that would necessarily mean alignment with the flourishing of all life, and in fact I've said that the goal of building aligned AI is to help life flourish, but not that AI should be aligned to all life directly. Now that we are much closer to building artificial superintelligence and need to figure out how to align it, the importance of aligning to non-human life stands out to me as a near-term priority.
For example, I can imagine us building human-aligned AI that ignores the plight of factory farmed animals, the suffering of shrimp, and the pain of bugs because lots of humans don't seem to care that much about their conditions. Such an AI would perhaps not be perfectly aligned in the ideal way we originally imagined aligned AI would be, but it would certainly be a kind of alignment with human goals, and it would be a travesty for the non-human beings it left out.
So let's not do that. Let's figure out how to align AI so that it's not just good for a few people or even all people, but so that it's good for all beings everywhere.
Cross-posted from my blog, Uncertain Updates.