Language models can't play chess, right?♟️ Excited to share our latest experiment that let's you play chess against a Gemini model!
4115912.6K
Eric Malmi✓
@ericmalmi
post-training @ Lovable | adjunct prof @ Aalto | ex-Google DeepMind
859 Following1.3K Followers364 Posts
- 🚨 New preprint on creative chess puzzle generation with diffusion models is out! ♟️ In his exceptional MSc thesis, @AatuSelkee introduced a new RL recipe on top of a masked diffusion model improving the previous SOTA. We're open-sourcing the model and releasing a demo 🚀 1/n
23201.8K - Posts @ericmalmi@AatuSelkee Diffusion models allow us to naturally condition the generation of the puzzles with a partial board, best move, and themes. Try out our demo at: 4/n
11181 - Posts @ericmalmi@AatuSelkee 📜 Paper: 💻 Demo: 📦 Code: This was a great collaboration with @AatuSelkee @SeveriRissanen @Xidong_Feng and @TZahavy 🙏 5/500186
- I had the privilege of sitting down with @kchonyc for our new AI podcast "And humanity created intelligence". we discussed the backstory behind the attention paper as well as... 🧵
13125.9K - Posts @ericmalmi- is recurrence making a comeback in LLMs? - how does Kyunghyun select problems to work on? - advice for students - why was coming to Finland 🇫🇮 among the best decisions he has made? Youtube: Spotify:101365
- Posts @ericmalmithe podcast is done with my co-host @arnosolin (who was traveling when we recorded this episode), @AaltoUniversity and ELLIS Institute Finland001104
- Eric MalmiRT @katarinaslama: I joined Aalto University's podcast "And humanity created intelligence" for an episode on AI safety, including the recent OpenAI / Hugging Face attack. Many thanks to @ericmalmi and @arnosolin for a great conversation!0205
- Eric MalmiRT @PetarV_93: Poster Spotlight! 🔦 Mastering Board Games by External and Internal Planning with Language Models ♟️ On Wednesday (Poster Session 3 East) Presented by Jakub Adamek and @ericmalmi010664
- Eric MalmiRT @arena: 🚨Breaking: New Gemini-2.5-Pro (06-05) takes the #1 spot across all Arenas again! 🥇 #1 in Text, Vision, WebDev 🥇 #1 in Hard, Coding, Math, Creative, Multi-turn, Instruction Following, and Long Queries categories Huge congrats @GoogleDeepMind!Google DeepMind @GoogleDeepMindGemini 2.5 Pro - our most intelligent model, is getting an update before general availability. ✨ It’s even better at: coding 🖥️, reasoning 💡, and creative writing ✍️ Learn more. 🧵01200311K
Google DeepMind@GoogleDeepMindGemini 2.5 Pro - our most intelligent model, is getting an update before general availability. ✨ It’s even better at: coding 🖥️, reasoning 💡, and creative writing ✍️ Learn more. 🧵933583.6K705K- thank you for the recognition @GaryMarcus! there's room for improvement, but I find it quite remarkable that an LLM learns to play creative sacrifices like this (best move according to Stockfish)
Gary Marcus @GaryMarcus@cfchabris @ericmalmi has kind of done that and it does pretty well except in weird positions - where it still sometimes make illegal moves. Confirming your conjecture and mine, if I understand his results correctly.0010598 
Posts @cfchabris@cfchabris @ericmalmi has kind of done that and it does pretty well except in weird positions - where it still sometimes make illegal moves. Confirming your conjecture and mine, if I understand his results correctly.003747- Eric MalmiRT @arena: 🚨Breaking: @GoogleDeepMind’s latest Gemini-2.5-Pro is now ranked #1 across all LMArena leaderboards 🏆 Highlights: - #1 in all text arenas (Coding, Style Control, Creative Writing, etc) - #1 on the Vision leaderboard with a ~70 pts lead! - #1 on WebDev Arena, surpassing Claude for the first time This is the first-ever sweep across text, vision, and WebDev by any model!🥇 Huge congrats to @GoogleDeepMind on this incredible breakthrough!Google DeepMind @GoogleDeepMindWe’re releasing an updated Gemini 2.5 Pro (I/O edition) to make it even better at coding. 🚀 You can build richer web apps, games, simulations and more - all with one prompt. In @GeminiApp, here's how it transformed images of nature into code to represent unique patterns 🌱02100532K
- Google DeepMind@GoogleDeepMindWe’re releasing an updated Gemini 2.5 Pro (I/O edition) to make it even better at coding. 🚀 You can build richer web apps, games, simulations and more - all with one prompt. In @GeminiApp, here's how it transformed images of nature into code to represent unique patterns 🌱1105063.4K856K
- Eric MalmiRT @GeminiApp: Think you can outsmart Gemini? We challenge you to a chess match! Play Gemini in a game of chess with our newest Gem: Chess champ. Explore different openings as you banter back and forth with Gemini. Available in the Gemini web app. ♟️Can you beat it? →0108059.5K
- multiple long-time dreams coming true at once: ✅ give a talk at NeurIPS ♟️ play chess on a stage 🤡 make my international debut as a rapper thanks to the audience for a lively discussion that went on for a good hour after the talk and to my amazing co-presenters @anianruoss @weballergy @MatejJusup!
27353.6K - Posts @ericmalmiour work establishes new test-time scaling results for chess-playing LLMs ♟️📈 honestly, I think it's quite mind blowing that an LLM can learn to perform minimax tree search within a single model call and smoothly improve its Elo the more output tokens you give it 🤯
1313508 - Posts @ericmalmitry playing against our no-search model at: and check out the paper:11204K
- Eric MalmiRT @justinxzhao: LLMs can play chess! In-context minimax search bootstrapped with values from Stockfish, implemented in Gemini. Paper: Breadth 4, depth 2, you start running out of context window. Chess Elo improves with more test-time compute. Really cool work from @ericmalmi @GoogleDeepMind0504.2K
