Monthly Archives: August 2016

Puppy love and cattachment theory.

Secure attachment and the limbic system

A couple of friends recently asked me for my take on this article by Nora Samaran on secure attachment and autonomy. The article focuses on the sense of security that comes from someone consistently responding positively to requests for comfort. The key point is that it's not just a quantitative thing, where you accumulate enough units of comfort and feel good. It's about really believing on a gut level that someone is willing to be there for you, and wants to do so: Continue reading

Minimum viable impact purchases

Several months ago I did some work on a trial basis for AI Impacts. It went well enough, but the process of agreeing in advance on what work needs to be done felt cumbersome. It's not uncommon that midway through a project, it turns out that it makes sense to do a different thing than what you'd originally envisioned - and because I was doing this for someone else, I had to check in at each such point. This didn't just slow down the process, but made the whole thing less motivating for me.

Later, I did my own research project. When natural pivot points came up, this didn't trigger a formal check-in - I just continued to do the thing that made the most sense. I think that I did better work this way, and steered more quickly towards the highest-value aspect of my research. Part of this is because, since I wasn't accountable to anyone else for the work, I could follow my own inner sense of what needed to be done.

I was talking with Katja about my work, and she mentioned that AI Impacts might potentially be interested in funding some of this work. I explained the motivation problem mentioned in the prior paragraphs, and wondered out loud whether AI Impacts might be interested in funding projects retrospectively, after I'd already completed them. Katja responded that in principle this sounded like a much better deal than funding projects prospectively, in large part because it would take less management effort on her part. This also felt like a much better deal to me than being funded prospectively, again because I wouldn't have to worry so much about checking in and fulfilling promises.

I've talked with friends about this consideration, and a few mentioned the fact that sometimes people are hired as researchers with a fairly vague or flexible research mandate, or prefunded to do more like their prior work, in the hope that they'll produce similarly valuable work in the future. But making promises like that, even if very abstract, also makes it difficult for me to proceed in a spirit of play, discovery, and curiosity, which is how I do some of my best work.

It also offends my sense of integrity to accept money for the promise to do one thing, or even one class of thing, when my real plan is to adopt a flexible stance - my best judgment might tell me to radically change course, and at this stage I fully intend to listen to it. For instance, I might decide that I should switch from research to writing and advocacy (what I'm doing now). I might even learn something that persuades me to make a bigger commitment to another course of action, starting or join some organization with a better-defined role.}

What doesn't offend my sense of integrity is to accept money explicitly for past work, with no promises about the future.

Then it clicked - this is the logic behind impact certificates. Continue reading

Some excerpts from Catistotle's Kittycatean Ethics

Every art and every inquiry, and likewise every action and pounce, seems to aim at some red dot, and hence it has been beautifully said that the red dot is that at which all cats aim. But a certain difference is apparent among ends, since some are ways of being at play, while others are certain kinds of works produced, over and above the being-at-play.
[...]
If, then, there is some end of the things we do that we want on account of itself, and the rest on account of this one, and we do not choose everything on account of something else (for in that way the pounces would go beyond all bounds, so that desire would be empty and pointless), it is clear that this would be the red dot, and in fact the reddest dot. Then would not an awareness of it have great weight in one's life, so that, like mousers who see a mouse, we would be more apt to hit on what is needed? But if this is so, one ought to try to get a grasp, at least in outline, of what it is and to what kind of knowledge or capacity it belongs.
[...]
And it would seem to belong to the one that is most governing and most a master art, and politics appears to be of this sort, since it prescribes which kinds of knowledge ought to be in the cities, and what sorts each cat ought to learn and to what extent; also, we see that the most honored capacities, such as mousing, household cattery, and meowing skill, are under this one. Since this capacity makes use of the rest of the kinds of knowledge, and also lays down the law about what one ought to do and from what one ought to refrain, the end of this capacity should include the ends of the other pursuits, so that this end would be the feline red dot. For even if the red dot is the same for one cat and for a city, that of the city appears to be greater, at least, and more complete both to achieve and to preserve; for even if it is achieved for only one cat that is something to be satisfied with, but for a litter or for cities it is something more beautiful and more divine. So our pursuit aims at this, and is in a certain way political.
[...]
Now taking up the thread again, since every kind of knowing and every pounce reach toward some red dot, let us say what it is that we claim politics aims at, and what, of all the dots aimed at by action, is the reddest. In name, this is pretty much agreed about by the majority of cats, for most cats, as well as those who are more refined, say it is being in a box, and assume that living well and doing well are the same thing as being in a box. But about being in a box-what it is-they are in dispute, and most cats do not give the same account of it as the wise. Some cats take it to be something visible and obvious, such as pleasure or wealth or honor, and different ones say different things, and even the same cat often says different things; when sick one thinks it is health, but when poor, that it is wealth, and when they are conscious of ignorance in themselves, cats marvel at those who say it is something grand and above them. And some cats believe that, besides these many red dots, there is some other red dot, by itself, which is also responsible for the being red of all these other dots.

Lessons learned from modeling AI takeoffs, and a call for collaboration

I am now able to think about things like AI risk and feel like the concepts are real, not just verbal. This was the point of my modeling the world project. I’ve generated a few intuitions around what’s important in AI risk, including a few considerations that I think are being neglected. There are a few directions my line of research can be extended, and I’m looking for collaborators to pick this up and run with it.

I intend to write about much of this in more depth, but since EA Global is coming up I want a simple description to point to here. These are just loose sketches, so I'm trying to describe rather than persuade.

New intuitions around AI risk

  • Better cybersecurity norms would probably reduce the chance of an accidental singleton.
  • Transparency on AI projects’ level of progress reduces the pressure towards an AI arms race.
  • Safety is convergent - widespread improvements in AI value alignment improve our chances at a benevolent singleton, even in an otherwise multipolar dynamic.

Continue reading

Yell at Mars to call swans

GLENDOWER. I can call spirits from the vasty deep.

HOTSPUR. Why, so can I, or so can any man;

But will they come when you do call for them?

- Shakespeare, Henry IV, Part 1

Calling swans

Recently a dear friend invited me to join them as they took their wedding photos, at the Palace of Fine Arts. There's a pond next to the structure, and across the pond we saw one of the swans who reside there. Someone observed that it would have been nice to take a picture with the swan. So I called out, in a loud and clear voice, "Excuse me! Would you come over here?" and beckoned. Repeatedly.

I was pretty sure that it wouldn't work. Swans don't understand spoken language. Even if they did, as far as I could tell they have no plausible motive to respond.

The swan turned towards us and swam halfway across the pond. As it slowed down, my companions thought of more ways to get its attention, ways that seemed more likely to work on a swan, like tossing things into the water. But my plan did more than nothing.

It's an important skill, to be able to come up with plans like that. Sometimes you need to notice when things are impossible, and give up. But other times, it's worth at least trying the plan "yell at the swan."

What heuristic was I using? I'm not sure, but I think it has to do with noticing that my model of the world is incomplete. Continue reading