Machine super intelligence

By Shane Legg, Marcus Hutter, W. Johnson. 2008

65 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Alignment & RLHF

Citations in the corpus

The Arcade Learning Environment: An Evaluation Platform for General Agents (2012, background): “To this end, different theoretical frameworks have been proposed to formalize the notion of “big” artificial intelligence (e.g., Russell, 1997; Hutter, 2005; Legg, 2008).”
Measuring Intelligence through Games (2011, methodology): “We refer the interested reader to a comprehensive treatment of the subject matter in Legg (2008).”
Space-Time Embedded Intelligence (2012, background): “In both Legg’s definition of intelligence [4] (based on AIXI [3]) and Russell’s bounded-optimality framework [10] (which embraces time and space constraints on the program of the agent), the agent is separated from the environment and therefore immortal.”
Measuring universal intelligence: Towards an anytime intelligence test (2010, background): “In fact, in Legg's Ph.D. dissertation (section 3.1.7) [Legg 2008], it is shown that sequence prediction (which is used in Hernandez-Orallo and Dowe and Hajek's works) is a special case of what they call chronological environments (which is used in Universal Intelligence).”
Statistical Language Models Based on Neural Networks (2012, background): “More theoretical reasons for using entropy as a measure of performance come from an artificial intelligence point of view [42].”
Information-Theoretic Bounded Rationality (2015, background): “In agent design, it became especially apparent more recently, as we continue to struggle in tackling problems of moderate complexity in spite of our deeper understanding of the planning problem [Duﬀ, 2002, Hutter, 2004, Legg, 2008, Ortega, 2011] and the vast computing power available to us.”
Position: Levels of AGI for Operationalizing Progress on the Path to AGI (2023, unknown): “Legg (Legg, 2008) and Goertzel (Goertzel, 2014) popularized the term AGI among computer scientists in 2001 (Legg, 2022), describing AGI as a machine that is able to do the cognitive tasks that people can typically do.”