1/N I’ve long believed that board games should play a bigger role in AI evaluation. They naturally test strategic reasoning, long-term planning, adaptation—and they can’t be solved by brute force or memorization. Game Arena is transparent, replayable, and tests actual behavioral intelligence.

A year after our trip to AAMAS in New Zealand, @sharky6000.bsky.social came back for more! I should have planned my year not to miss @aamasconf.bsky.social… Big congrats and keep up amazing work! 🎉👏

Looking forward to speaking at the ML Pub Club on June 3rd! I'll discuss how, during my time at DeepMind, we taught LLMs to play chess at a GM level and the broader implications for strategic AI. If you're in Zagreb, join us at Mažuranićev trg 13 at 6 PM! More info & RSVP: lu.ma/erjji5it

A paper from my time at Google was accepted for a spotlight presentation at ICML! In “Mastering Board Games by External and Internal Planning with Language Models”, we show how language models can achieve grandmaster-level play using a search budget on par with humans. arxiv.org/abs/2412.12119

Hive (and all of its expansions) has been added to OpenSpiel! 🎉🤩🐝🐜🕷️🐞🦟🪲 From Gen42: "Hive is an award-winning board game with a difference. There is no board. The pieces are added to the playing area thus creating the board. As more and more pieces are added the game becomes a fight to ... 🧵1/5

www.youtube.com/watch?v=9_Pe... An interview with Rich. The humility of Rich is truly inspiring: "There are no authorities in science". I wish people would listen and live by this.

Sim agents are key for developing autonomous systems for safety-critical systems, like self-driving cars. We're open-sourcing sim agents that achieve a 99.8% success rate with < 0.8% failures on the Waymo Dataset. These agents are built through scaling self-play.

We've released our lecture notes for the course Probabilistic AI at ETH Zurich, covering uncertainty in ML and its importance for sequential decision making. Thanks a lot to @jonhue.bsky.social for his amazing effort and to everyone who contributed! We hope this resource is useful to you!

LLMs Mastering Board Games: ZurichNLP Meetup - Feb 20th! Excited to share insights from my student research at Google DeepMind at the upcoming ZurichNLP meetup! I'll present how we achieved high-level play in board games using LLMs with a search budget comparable to human chess grandmasters.

I've been talking about writing this paper to anyone who would listen since 2020. I bombed a bunch of job talks trying to convince companies to work on this. It's so nice to finally just be able to say, yes, self-play RL in a diverse world gives you immense capabilities arxiv.org/abs/2502.03349

I am more than happy that @quantamagazine.bsky.social , which I have been reading since the first year of my Bachelor's degree, cited us: www.quantamagazine.org/chatbot-soft... More news about this work and 2nd version is coming soon! #machinelearning #deeplearning #cs #computerscience #tcs

Pet peeve: Calling something that’s not open source… open source. Open weight != open source

A typical European car is parked 92% of the time. It spends 1/5th of its driving time looking for parking. Its 5 seats only move 1.5 people. 86% of its fuel never reaches the wheels, and most of the energy that does, moves the car, not the people. Sound efficient? HT @ellenmacarthurfdn.bsky.social

An interesting idea that’s worth keeping an eye on!

Demis Hassabis, James Manyika, and I wrote up an overview of the AI research work & advances across Google in 2024 (Gemini, NotebookLM, robotics, ML for science, & advances in responsible AI+more). 🎊 Given it a read or paste it into NotebookLM to listen, if you prefer! blog.google/technology/a...

Check out the 16th Workshop on Optimization and Learning in Multiagent Systems (OptLearnMAS-25) at #AAMAS 2025! Topics: distributed opt., coalition formation, opt. under uncertainty, winner determination algs in auctions and procurements, algs to compute equilibria in games. optlearnmas.github.io

In December, I posted about our new paper on mastering board games using internal + external planning. 👇 Here's a talk now on Youtube about it given by my awesome colleague John Schultz! www.youtube.com/watch?v=JyxE...

John's talk is now available online! www.youtube.com/watch?v=JyxE...

Join John's talk to get insights on our paper on mastering board games with language models!

Just a reminder that the AAMAS Doctoral Consortium deadline is next Friday! Please consider submitting to this great venue or telling your students about it. 👇

After 15 years away from competitive chess, I forgot how much thrill and excitement the game gives! ♟️ I decided to attend a tournament with five grandmasters and numerous international, fide, and candidate masters. @lichess.org broadcast: lichess.org/broadcast/29...

If you are into ML theory (RL or not) with a proven track record, and you are interested in an industry research position, PM me. Feel free to spread the word.

After a slight delay, it is now also out on arXiv: arxiv.org/abs/2412.12119

I will remember @neuripsconf.bsky.social 2024 as a defining moment in my career. Grateful to mentors & colleagues at @ethzurich.bsky.social and @deepmind.google.web.brid.gy for making it possible. Meeting enthusiastic researchers and having insightful, constructive discussions was truly inspiring!

Don’t miss this talk by @sharky6000.bsky.social if you want to turn LLMs into interactive, gamified chatbots!

I was honored to present our demo on “Mastering Chess With Language Models” at the @GoogleDeepMind booth at @NeurIPSConf right before an inspiring talk by Jeff Dean Thanks to everyone who dropped by and made it a memorable session! ♟️

if you're at #NeurIPS2024, want to learn how to make LLMs really good at chess, and see a live demo, come and visit the Google DeepMind booth tomorrow at 9:30 am!

I couldn’t ask for a better @neuripsconf.bsky.social welcome! Spotted a lovely family playing chess and had the joy of facing a brilliant 6-year-old who just learned the game 3 days ago. Her enthusiasm was truly inspiring!

I will be showing a “Mastering Chess With Language Models” demo at @googledeepind.bsky.social booth at @neuripsconf.bsky.social with @ericmalmi.bsky.social @nenadtomasev.bsky.social @anianruoss.bsky.social Don't hesitate to reach out if interested or want to chat! deepmind.google/discover/eve...

𝗚𝗼𝗼𝗱 𝗲𝗻𝗼𝘂𝗴𝗵 𝗮𝘁 𝗰𝗵𝗲𝘀𝘀 𝘁𝗼 𝗼𝘂𝘁𝘀𝗺𝗮𝗿𝘁 𝗮 𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗺𝗼𝗱𝗲𝗹? ♟️ 𝗚𝗶𝘃𝗲 𝗶𝘁 𝗮 𝘀𝗵𝗼𝘁! 👉 gemini.google.com/gem/chess-ch... Share your victories (and brags) in the comments!

"𝗖𝗮𝗻 𝗰𝗵𝗲𝘀𝘀 𝗮𝗻𝗱 𝗼𝘁𝗵𝗲𝗿 𝗯𝗼𝗮𝗿𝗱 𝗴𝗮𝗺𝗲𝘀 𝘀𝘁𝗶𝗹𝗹 𝗮𝗱𝗱 𝘃𝗮𝗹𝘂𝗲 𝘁𝗼 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵?” I was fortunate to join the board games team at Google as a student researcher, where we proved that the answer is a resounding YES! ♟️🤯 deepmind.google/research/pub...

Super happy to reveal our new paper! 🎉🙌♟️ We trained a model to play four games, and the performance in each increases by "external search" (MCTS using a learned world model) and "internal search" where the model outputs the whole plan on its own!

The project I was quite honored to work on! ♟️ As a chess enthusiast, I was especially thrilled that an LLM equipped with an efficient MCTS reaches grandmaster-level strength with a search budget comparable to human players! 🤯 deepmind.google/research/pub...