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! 🤯.

Looking forward to speaking at the ML Pub Club on June 3rd! . I'll discuss how, during my time at @GoogleDeepMind, we taught LLMs to play chess at a GM level and the broader implications for strategic AI. If you're in Zagreb, check the details & RSVP:

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 LMs can achieve GM-level play using a search budget on par with humans.

RT @karl_tuyls: 🚀 What is an agent? A question that’s been tackled for decades is now resurfacing as we enter the next phase of frontier AI….

i am excited about my talk on mastering board games with LLMs at the @zurichnlp meetup hosted by @ETH_AI_Center!. registrations are still open.

🗓️ 20th Feb 2025, 18:00-20:00.📍 Zürich, OAT ETH Zurich (14th floor).🔗

Join the conversation! We'll cover:.• The innovative search strategies we developed .• The implications of LLMs in strategic domains .• Q&A and networking with fellow AI enthusiasts.

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

RT @YiMaTweets: Also, many of my students and colleagues working in the field of AI feel that there is an unfair competition between the ac….

RT @Swarooprm7: Deepseek is great, but don't read too much into its lead on humanity's last exam benchmark by @DanHendrycks et. al. The dat….

RT @MathMatize: Cauchy sequences in an incomplete space

RT @polynoamial: Lots of vague AI hype on social media these days. There are good reasons to be optimistic about further progress, but plen….

John's talk is now available online!.

RT @behrouz_ali: Attention has been the key component for most advances in LLMs, but it can’t scale to long context. Does this mean we need….

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

RT @ilijabogunovic: 10 days into the new year and some exciting ideas in LLM reasoning, rStar-Math: MCTS paired with a novel code-augmented….

Sample games in the appendix:

I couldn't explain earlier why I sometimes experience increased disagreements upon presented facts while arguing with colleagues I highly value, but this perfectly captures the essence!.

The first round was a hard-fought win against a much lower-rated opponent, but it is a testament to the increased playing quality since the recent global chess boom! .

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 broadcast:

RT @alexandrabotez: Highly recommend playing classical chess. You are not allowed any electronics and generally play in silence for ~4 hour….