MIRI Updates
For many years, MIRI’s goal has been to resolve enough fundamental confusions around alignment and intelligence to enable humanity to think clearly about technical AI safety risks—and to do this before this technology advances to the point of potential catastrophe....
This is the conclusion of the Embedded Agency series. Previous posts: Embedded Agents — Decision Theory — Embedded World-ModelsRobust Delegation — Subsystem Alignment A final word on curiosity, and intellectual puzzles: I described an embedded agent, Emmy,...
[mathjax] You want to figure something out, but you don’t know how to do that yet. You have to somehow break up the task into sub-computations. There is no atomic act of “thinking”; intelligence must be built up of...
[mathjax] Because the world is big, the agent as it is may be inadequate to accomplish its goals, including in its ability to think. Because the agent is made of parts, it can improve itself and become more capable. Improvements...
[mathjax] An agent which is larger than its environment can: Hold an exact model of the environment in its head. Think through the consequences of every potential course of action. If it doesn’t know the environment perfectly, hold...
[mathjax] Decision theory and artificial intelligence typically try to compute something resembling $$\underset{a \ \in \ Actions}{\mathrm{argmax}} \ \ f(a).$$ I.e., maximize some function of the action. This tends to assume that we can detangle things enough to see...