Building a safe AI is not about taking an unsafe AI and tacking on rules of what not to do. Building a safe AI is about creating it so that it only seeks to do the right things in the first place.
In other words: a mind has a potentially infinite amount of actions it could take. The main difficulty is locating the right course of action in the first place. Since there are potentially an infinite amount of ways for a mind to search that space of actions, the question is not "how do we prevent a mind from doing thing X" but rather "how do we make a mind to do thing Y". The amount of things we wouldn't want it to do is vastly larger than the amount of things we'd want it do. Human values are complex, and only a small portion of all possible universes actually match our values. A safe AI does not have all of the properties of a "regular AI", for the two may have been built do search the space of actions in entirely different ways.
Well, then its pretty easy, isn't it? You set the fitness function as predicting what you would want it to do. It then does its best to predict all of your values and desires and decision making. I suppose that would only work for one person, but it can be applied on a larger scale. Suppose you have a code of ethics that a group like SIAI comes up with and approves. You then feed it to the intelligence and test it under various simulations to make sure that it is interpretting them correctly and learns how to. The thing is that all you have to do to make it unsafe is remove those goals, go back to the basic program and give it orders that would require it to do bad things, like a military robot. Boom goes the world.
Now is the very last minute to apply for a Summer 2010 Visiting Fellowship. If you’ve been interested in SIAI for a while, but haven’t quite managed to make contact -- or if you’re just looking for a good way to spend a week or more of your summer -- drop us a line. See what an SIAI summer might do for you and the world.
(SIAI’s Visiting Fellow program brings volunteers to SIAI for anywhere from a week to three months, to learn, teach, and collaborate. Flights and room and board are covered. We’ve been rolling since June of 2009, with good success.)
Apply because:
Apply especially if:
(You don’t need all of the above; some is fine.)
Don’t be intimidated -- SIAI contains most of the smartest people I’ve ever met, but we’re also a very open community. Err on the side of sending in an application; then, at least we’ll know each other. (Applications for fall and beyond are also welcome; we’re taking Fellows on a rolling basis.)
If you’d like a better idea of what SIAI is, and what we’re aimed at, check out:
1. SIAI's Brief Introduction;
2. The Challenge projects;
3. Our 2009 accomplishments;
4. Videos from past Singularity Summits (the 2010 Summit will happen during this summer’s program, Aug 14-15 in SF; visiting Fellows will assist);
5. Comments from our last Call for Visiting Fellows; and/or
6. Bios of the 2009 Summer Fellows.
Or just drop me a line. Our application process is informal -- just send me an email at anna at singinst dot org with: (1) a resume/c.v. or similar information; and (2) a few sentences on why you’re applying. And we’ll figure out where to go from there.
Looking forward to hearing from you.