There isn’t really a general answer to “how to design a safe AI”. It really depends what the AI is used for (and what they mean by AI).
For recursively self-improving AI, you’ve got your choice of “it’s always bad”, “You should only do it the SIAI way (and they haven’t figured that out yet)”, or “It’s not a big deal, just use sofware best practices and iterate”.
For robots, I’ve argued in the past that robots need to share our values in order to avoid squashing them, but I haven’t seen anyone work this out rigorously. On a different tack altogether, Ron Arkin’s Governing Lethal Behavior in Autonomous Robots is excellent and describes in detail how to make military robots that use lethality appropriately. In a household application, it’s very difficult to see what sorts of actions might be problematic, but in a military application the main concern is making “aim the gun and fire” only happen when you really want it to.
For video games and the like, there’s plenty of literature about the question, but not much to take seriously there.
There isn’t really a general answer to “how to design a safe AI”. It really depends what the AI is used for (and what they mean by AI).
For recursively self-improving AI, you’ve got your choice of “it’s always bad”, “You should only do it the SIAI way (and they haven’t figured that out yet)”, or “It’s not a big deal, just use sofware best practices and iterate”.
For robots, I’ve argued in the past that robots need to share our values in order to avoid squashing them, but I haven’t seen anyone work this out rigorously. On a different tack altogether, Ron Arkin’s Governing Lethal Behavior in Autonomous Robots is excellent and describes in detail how to make military robots that use lethality appropriately. In a household application, it’s very difficult to see what sorts of actions might be problematic, but in a military application the main concern is making “aim the gun and fire” only happen when you really want it to.
For video games and the like, there’s plenty of literature about the question, but not much to take seriously there.