https://hackerpaper.kaipfister.de/p/cs_0004001/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=32537130urn:hackerpapers:mention:cs_0004001:32537130Sun, 21 Aug 2022 03:22:24 GMT<p>&gt; It is a term gaining in popularity due to this difficult to define definition and allows for more a porn like definition &gt; Philosophers, psychologists, neuroscientists, and many others have been contemplating the definition of intelligence for centuries and we&#x27;re still not -quite there Given the decade-old, seminal, widely cited papers by Legg (co-founder of Deepmind) &amp; Hutter (long-term professor of ANU with multiple awards, currently researcher at Deepmind) titled &quot;Universal Intelligence: A Definition of Machine Intelligence&quot;[1] and &quot;A Collection of Definitions of Intelligence&quot;[2] and the…</p><p><a href="https://hackerpaper.kaipfister.de/p/cs_0004001/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AIhttps://news.ycombinator.com/item?id=27687520urn:hackerpapers:mention:cs_0004001:27687520Wed, 30 Jun 2021 12:12:14 GMT<p>The origins of the approach of a perfect world model equals AI, at least how I encountered it, are from Marcus Hutter. H proved that perfect compression (=prediction of what will happen next) is the ideal way to drive an agent in reinforcement learning[1] (the choice of action being the likeliest high-reward action). So a perfect world model is enough to win at reinforcement learning. Can you show that if you maximized reward in some RL problem, it means you necessarily built a perfect world-model? [1] A Theory of Universal Artificial Intelligence based on Algorithmic Complexity, 2000…</p><p><a href="https://hackerpaper.kaipfister.de/p/cs_0004001/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AIhttps://news.ycombinator.com/item?id=10981615urn:hackerpapers:mention:cs_0004001:10981615Wed, 27 Jan 2016 17:56:55 GMT<p>From the conclusions of http://arxiv.org/abs/cs/0004001 : &quot;All tasks which require intelligence to be solved can naturally be formulated as a maximization of some expected utility in the framework of agents. We gave a functional (2) and an iterative (9) formulation of such a decision theoretic agent, which is general enough to cover all AI problem classes, as has been demonstrated by several examples. The main remaining problem is the unknown prior probability distribution AI of the environment(s). &lt;...&gt; the universal semimeasure, based on ideas from algorithmic information theory, solves the…</p><p><a href="https://hackerpaper.kaipfister.de/p/cs_0004001/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AI