An Approximation of the Universal Intelligence Measure · HackerPapers discussions

An Approximation of the Universal Intelligence Measure — mentioned by chriswarbo

Thu, 05 Jan 2023 12:06:25 GMT

https://arxiv.org/abs/cs/0605024 gives a formal model of intelligence (achieving high reward in an agent/environment setup, across all computable environments weighted by their Kolmogorov complexity) https://arxiv.org/abs/1109.5951 gives a computable approximation (dubbed AIQ, Algorithmic Intelligence Quotient), and a reference implementation using Brainfuck programs (personally I would prefer Binary Combinatory Logic or Binary Lambda Calculus ;) )

Paper and discussion history. A mention is not an endorsement.

An Approximation of the Universal Intelligence Measure — mentioned by khiner

Thu, 27 Apr 2017 07:06:22 GMT

For a much better and more constructive read toward the effort of a stringent definition of intelligence, I would recommend anything from Shane Legg - most pragmattically this: https://arxiv.org/pdf/1109.5951v2.pdf

Paper and discussion history. A mention is not an endorsement.

An Approximation of the Universal Intelligence Measure — mentioned by chriswarbo

Thu, 18 Dec 2014 12:06:24 GMT

I appreciate Brainfuck for its originality, but I agree with the grandparent that its influence on "esoteric languages" is too strong. Not only are many "esoteric languages" just Brainfuck+something (eg. http://esolangs.org/wiki/Category:Brainfuck_derivatives ), but also having Brainfuck as the default "minimalist language" is also unfortunate. For example, a NASA study on self-replicating machines ( http://www.niac.usra.edu/files/studies/final_report/883Toth-... ) mentions it on page 43: > ...we thought that our Controller subsystem should also be as simple as possible. We spent quite a bit…

Paper and discussion history. A mention is not an endorsement.