BOOK · [4957]
Machine Super Intelligence
Science
Shane Legg's doctoral dissertation (supervised by Marcus Hutter), published as a standalone monograph, builds a formal theory of universal intelligence grounded in algorithmic information theory, Solomonoff induction, and the AIXI model, and proposes a measure of intelligence as the ability to achieve goals across a wide range of environments. It is the only full book-length monograph on Ilya's Carmack reading list, reflecting his conviction that compression, Kolmogorov complexity, and a rigorous definition of intelligence are foundational to understanding what learning machines actually do.
Endorsed By
1 PERSON-
Ilya Sutskever
“If you really learn all of these, you'll know 90% of what matters today.”
Appears on the ~30-item reading list Ilya Sutskever gave John Carmack ("if you really learn all of these, you'll know 90% of what matters today"), listed as 'Machine Super Intelligence.' The list is reproduced in multiple consolidated copies after Carmack described it publicly; no reliable trade ISBN is published for this Lulu/self-published 2008 dissertation.
Found on
1 SOURCE- github.com · ilya sutskever recommended reading reading list