815 karmaJoined Working (0-5 years)Oxford, UK


Thanks for the comment (and welcome to the Forum! :) ). Yeah using conditional oughts seems like a pretty reasonable approach to me, though of course has some convenience cost when the Z is very widely shared ('you ought to fix your brakes over drive without brakes in order to not crash') so can perhaps then be implied.

Great post, and an interesting counterfactual history!

Hooray for moral trade.

Evolutionary debunking arguments feel relevant re the causal history of our beliefes.

One thing I have heard is that having long-ish application stages provides value by getting more people to think about relevant topics (I have heard this from at least two orgs I think). E.g. having several hundred people spend an hour writing a paragraphs about an AI safety topic might be good by virtue of generally having more people think more about this being good. I haven't seen a write-up weighing up the pros and cons of this though. I agree this can be bad for applicants.

NIce post!

We might then expect a lot of powerful attempts to change prevailing ‘human’ values, prior to the level of AI capabilities where we might have worried a lot about AI taking over the world. If we care about our values, this could be very bad. 

This seems like a key point to me, that it is hard to get good evidence on. The red stripes are rather benign, so we are in luck in a world like that. But if the AI values something in a more totalising way (not just satisficing with a lot of x's and red stripes being enough, but striving to make all humans spend all their time making x's and stripes) that seems problematic for us. Perhaps it depends how 'grabby' the values are, and therefore how compatible with a liberal, pluralistic, multipolar world.

Hmm true, I think I agree that this means the dynamics I describe matter less in expectation (because the positional goods-oriented people will be quite marginal in terms of using the resources of the universe).

Good point re aesthetics perhaps mattering more, and about people dis-valuing inequality and therefore not wanting to create a lot of moderately good lives lest they feel bad about having amazing lives and controlling vast amounts of resources.

Re "But I don't think ..." in your first paragraph, I am not sure what if anything we actually disagree about. I think what you are saying is that there are plenty of resources in our galaxy, and far more beyond, for all present people to have fairly arbitrarily large levels of wealth. I agree, and I am also saying that people may want to keep it roughly that way, rather than creating heaps of people and crowding up the universe.

Nice, good idea and well implemented!

In terms of wastewater being good for getting samples from lots of people at once and not needing ethics clearance, but being worse for respiratory pathogens, how feasible is airborne environmental DNA sampling? I have never looked into it, I just remember hearing someone give a talk about their work on this, I think related to this paper: https://www.sciencedirect.com/science/article/pii/S096098222101650X

I assume it is just hard to get the quantity of nucleic acids we would want from the air.

Flagging this for @Conrad K. - this seems like perhaps a better version of what you were considering building last year I think? If you have time you might have useful thoughts/suggestions.

I played around with the simulator a bit but didn't find anything too counterintuitive. I noticed various minor suboptimal things, depending on what you want to do with the simulator some of these may not be worth changing:

  • I found having many values in relative abundance box for nasal swabs a bit confusing and harder to manage as a user. Why not just specify a distribution with some parameters rather than list lots of possible values drawn from that distribution?
  • The line is not monotonic as it should be here, seemingly because the simulation hits 30% of the population and then stops. Maybe rather than have the line go back to 0, just stop it when it hits 30%, or have it plateau at 30%?
  • There were some issues with the sizing of the graph for me. I am using Chrome on Windows 11. At 100% zoom part of the x-axis label and the y-axis numbers are cut off:

    And the problem becomes worse if for whatever reason you run lots of scenarios, where the whole bottom half of the graph disappears:

Thanks for writing this up! Have you spoken to Christian Ruhl or anyone else at Founder's Pledge about this work? I think FP would be interested in and benefit from this.

I downvoted because there are lots of questions lumped in together without enough motivation and cohesion for my liking, and compared to e.g. the moral weights project the engagement with these subtle issues feels more flippant than serious.

Load more