A new simplicity measure for near-optimal computable predictions (based on the fastest way of describing objects, not the shortest).

A prior distribution summarises what is known about a variable in the absence of any observations. Solomonoffs universal prior combines Occam’s razor and the principle of multiple explanations. For which comp. classes do comp. universal priors exist?

"Finally, after so many years thinking about doing it, tonight at Bar Tra in Lugano, I, along with two other guys, launched a project to build an AGI. [..] 2007 is going to be a very interesting year."

An algorithm M is described that solves any well-defined problem p as quickly as the fastest algorithm computing a solution to p, save for a factor of 5 and low-order additive terms.

"A trick to building a safe super intelligence would be to require that its goals always consist of two parts: Firstly a specification of what is to be achieved, and secondly a specification of what resources can be used."

"Trying to prove that an AI is friendly is hard, trying to define “friendly” is hard, and trying to prove that you can’t prove friendliness is also hard. Although it is not the desired possibility, I suspect that the latter is actually the case."

The new millennium has brought substantial progress in the field of theoretically optimal and practically feasible algorithms for prediction, search, inductive inference, problem solving, decision making, and reinforcement learning.

Answers to some of the frequently asked questions received since the publication of the Gödel Machine TR in 2003.

Introduces a general and in a certain sense time-optimal way of solving one problem after another, efficiently searching the space of programs that compute solution candidates.

Gödel machines are self-referential universal problem solvers making provably optimal self- improvements.

Appears to prove that beyond a moderate level of complexity the development of powerful artificial intelligence algorithms can only be an experimental science.

Probably the largest collection of defintions of intelligence.

"I think the idea is an impossible dream, and it seems to me that both Ben and Izabela are pretty skeptical of it too."

"I think that the work they are doing is important as I think that AI could be dangerous, but I'm not sure in what way."

"We focus on machine learning, optimal universal artificial intelligence and optimal rational agents, operations research, complexity theory, and robotics." — I need to get there.

A PhD student of Marcus Hutter working on the theory of near-infinitely-powerful AGI who in past worked with Goertzel on the Webmind AI project in the late 1990's, and with Voss on the A2I2 project.