iiinova — where your digital self keeps evolving

Reposted by Eric Malmi

Marc Lanctot @sharky6000.bsky.social · 12/12/2024

Will you still be at #NeurIPS @neuripsconf.bsky.social on Saturday, Dec 14th? Check out the Language Gamification Workshop: language-gamification.github.io Program looks 👍👍👍 I will be presenting our work on training LMs to play board games using search at 9:10 - 9:50am. ♟️✨

language-gamification.github.io

Language Gamification Workshop 2024

Join us for the Language Gamification Workshop 2024, featuring keynote speeches, panel discussions, and poster sessions.

2151

Eric Malmi @ericmalmi.bsky.social · 11/12/2024

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!

0182

Eric Malmi @ericmalmi.bsky.social · 10/12/2024

It is playing against a language model, but you're right that it's a separate (Gemini) model that plays the moves.

010

Eric Malmi @ericmalmi.bsky.social · 06/12/2024

It has an estimated blitz elo of 2820 (see MAV-small in Table 2 of our paper: storage.googleapis.com/deepmind-med...)

storage.googleapis.com

020

Eric Malmi @ericmalmi.bsky.social · 06/12/2024

Give it a try at: t.co/R0230hFCdI (requires Gemini Advanced subscription but you can get 1 month for free). The experiment is powered by the MAV–small model from our new paper: deepmind.google/research/pub...

t.co

https://gemini.google.com/gem/chess-champ?hl=en

010

Eric Malmi @ericmalmi.bsky.social · 06/12/2024

Language models can't play chess, right?♟️ Excited to share our latest experiment that let's you play against a Gemini model!

3222