Marcus Hutter (@mhutter42) / X

Marcus Hutter

71 posts

Marcus Hutter

@mhutter42

I 👨‍🔬 a math. definition&theory of Artificial Super-Intelligence 🎥&🎤@ tinyurl.com/mhytc42 🍀 I now work @GoogleDeepMind 🧠 History:🇩🇪🇨🇭🇦🇺🇬🇧

London, UK

Joined April 2011

Pinned
Marcus Hutter
@mhutter42
May 25, 2024
My new book finally ships! You fear your math is not up to scratch? Fear not, over 100 pages are devoted to introducing the relevant concepts. routledge.com/An-Introductio… #AI #AGI #ArtificialIntelligence #Math #Maths #machinelearning #ReinforcementLearning
31K
Marcus Hutter
@mhutter42
Dec 24, 2024
Santa Arrived! The PDF (of a colorful Xmas version) of the "Introduction to Universal AI" book is now freely available online at hutter1.net/ai/uaibook2.htm Wishing you all joyful reading, Merry Xmas & a :-) New Year.
82K
Marcus Hutter
@mhutter42
Jul 20, 2022
Have you ever wondered why Deep Learning does not publish formal algorithms for their models while other CS disciplines such as Reinforcement Learning do? After 5 years of Transformers, here's some hopefully useful pseudocode:
arxiv.org
Formal Algorithms for Transformers
This document aims to be a self-contained, mathematically precise overview of transformer architectures and algorithms (*not* results). It covers what transformers are, how they are trained, what...
Marcus Hutter
@mhutter42
Aug 16, 2023
Ilya Sutskever explains how Kolmogorov complexity well-defines unsupervised learning and LLMs are approximations thereof. Nothing new but very accessible, and maybe it makes it more convincing if it comes from the Chief Scientist of OpenAI.
Jim Fan
@DrJimFan
Aug 16, 2023
There're few who can deliver both great AI research and charismatic talks. OpenAI Chief Scientist @ilyasut is one of them. I watched Ilya's lecture at Simons Institute, where he delved into why unsupervised learning works through the lens of compression. Sharing my notes: -
00:00
87K
Marcus Hutter
@mhutter42
Jun 8, 2025
I sense arxiv.org/abs/2505.17010 may be our last paper written without LLM help. As an experiment, we asked Gemini to formulate out and prove all claims made in Appendix E. It did a remarkably good job. The response is not included in the paper but here: hutter1.net/publ/tb-gemini…
57K
Marcus Hutter
@mhutter42
Aug 23, 2023
What do you get when you cross modern Machine Learning with good old-fashioned Search? An IJCAI distinguished paper award 🙂 for Levin Tree Search with Context Models: aihub.org/2023/08/23/con…
56K
Marcus Hutter
@mhutter42
Dec 3, 2024
'Foundations of Algorithmic Thermodynamics' accepted by 'Physical Review E'. *Algorithmic* entropy determines a system's actual capacity to do work from an *individual* state. Alg. versions of Jarzynski's equality & Landauer's principle & the Second Law.
arxiv.org
Foundations of algorithmic thermodynamics
Gács' coarse-grained algorithmic entropy leverages universal computation to quantify the information content of any given physical state. Unlike the Boltzmann and Gibbs-Shannon entropies, it...
6.2K
Marcus Hutter
@mhutter42
Jul 23, 2023
Progress on the Human Knowledge Compression front: Saurabh Kumar is the second winner of the 10x (1GB) version, winning €5187, by beating the previous record by 1.04%. Who wants to try next? prize.hutter1.net
16K
Marcus Hutter
@mhutter42
May 10, 2024
Are you interested in AGI but a bit exhausted keeping up with Deep Learning? Why not take a break and watch the Cartesian Cafe podcast covering (a tiny fraction of) my new book. youtube.com/watch?v=7TgOwM… #ai #artificialintelligence #math #maths #machinelearning
16K
Marcus Hutter
@mhutter42
Aug 25, 2025
Reflective-Oracle AIXI solves the Grain of Truth problem for super-intelligent multi-agent systems/societies. Finally the long-awaited more comprehensive treatment building upon earlier work from last decade is out. Slides: hutter1.net/publ/sgot.pdf Paper: arxiv.org/abs/2508.16245
7.3K
Marcus Hutter
@mhutter42
Jul 14, 2021
Progress on the Human Knowledge Compression front: Artemiy Margaritov is the first winner of the 10x (1GB) version, winning €9000, by beating the baseline by 1.1%. Who wants to try next? prize.hutter1.net
Marcus Hutter
@mhutter42
Jun 24, 2021
Thought: Excessive marketing is like an arms race and mostly a negative-sum game: If every (US) company halved their marketing budget, no company nor consumer would be worse off, and the savings and freed labor used productively could easily solve world poverty&hunger&more.
Marcus Hutter
@mhutter42
Aug 28, 2020
Panel discussion on GPT-3 and AGI (David, Susan, Marcus): Recording: youtu.be/aDFLp4A1EmY Lapsed invitation: eventbrite.com.au/e/a-discussion… Slides to the shortest introduction to the inner workings of GPT-3: hutter1.net/publ/sgpt3agi.…
Marcus Hutter
@mhutter42
Apr 16, 2025
"Bridging Algorithmic Information Theory and Machine Learning: Clustering, density estimation, Kolmogorov complexity-based kernels, and kernel learning in unsupervised learning" just got accepted by "Physica D: Nonlinear Phenomena" authors.elsevier.com/c/1kvzzc2EevpCC
2.4K