iiinova — where your digital self keeps evolving

Reposted by Manfred Diaz

Marc Lanctot @sharky6000.bsky.social · 14/07/2026

I'm delighted to announce the release of OpenSpiel 2.0! ♟️🎲♦️🎉 Structured types for states, observations, and actions, standard trajectories (based on JSON), 19 new games, AlphaZero ported to JAX, Windows PyPI support, language model fine-tuning examples and an MCP server (demo below 🤩👇)! 🧵 1/N

46713

Reposted by Manfred Diaz

Joel Z Leibo @jzleibo.bsky.social · 21/03/2026

New paper: “𝐀 𝐓𝐡𝐞𝐨𝐫𝐲 𝐨𝐟 𝐀𝐩𝐩𝐫𝐨𝐩𝐫𝐢𝐚𝐭𝐞𝐧𝐞𝐬𝐬 𝐓𝐡𝐚𝐭 𝐀𝐜𝐜𝐨𝐮𝐧𝐭𝐬 𝐟𝐨𝐫 𝐍𝐨𝐫𝐦𝐬 𝐨𝐟 𝐑𝐚𝐭𝐢𝐨𝐧𝐚𝐥𝐢𝐭𝐲” Agent-based models of social order work better when agents act by predictive pattern completion from prefix (culture/context) to suffix (action) than when they act through expected value maximization

43511

Reposted by Manfred Diaz

Marc Lanctot @sharky6000.bsky.social · 15/01/2026

Hello all! 👋 I’m delighted to share a 🚨 new preprint 🚨: “Active Evaluation of General Agents: Problem Definition and Comparison of Baseline Algorithms”. A paper thread! 🤩📄🧵 1/N

25712

Manfred Diaz @manfreddiaz.bsky.social · 23/05/2025

@aamasconf.bsky.social 2025 was very special for us! We had the opportunity. to present a tutorial on general evaluation of AI agents, and we got a best paper award! Congrats, @sharky6000.bsky.social and the team! 🎉

0121

Reposted by Manfred Diaz

Joel Z Leibo @jzleibo.bsky.social · 09/05/2025

Announcing our latest arxiv paper: Societal and technological progress as sewing an ever-growing, ever-changing, patchy, and polychrome quilt arxiv.org/abs/2505.05197 We argue for a view of AI safety centered on preventing disagreement from spiraling into conflict.

arxiv.org

Societal and technological progress as sewing an ever-growing, ever-changing, patchy, and polychrome quilt

Artificial Intelligence (AI) systems are increasingly placed in positions where their decisions have real consequences, e.g., moderating online spaces, conducting research, and advising on policy. Ens...

1236

Reposted by Manfred Diaz

Joel Z Leibo @jzleibo.bsky.social · 22/04/2025

First LessWrong post! Inspired by Richard Rorty, we argue for a different view of AI alignment, where the goal is "more like sewing together a very large, elaborate, polychrome quilt", than it is "like getting a clearer vision of something true and deep" www.lesswrong.com/posts/S8KYwt...

lesswrong.com

Societal and technological progress as sewing an ever-growing, ever-changing, patchy, and polychrome quilt — LessWrong

We can just drop the axiom of rational convergence.

351

Reposted by Manfred Diaz

Joel Z Leibo @jzleibo.bsky.social · 01/04/2025

In case folks are interested, here's a video of a talk I gave at MIT a couple weeks ago: youtu.be/FmN6fRyfcsY?...

youtu.be

A Theory of Appropriateness with Applications to Generative Artificial Intelligence

YouTube video by MITCBMM

073

Reposted by Manfred Diaz

Marc Lanctot @sharky6000.bsky.social · 28/03/2025

Our new evaluation method, Soft Condorcet Optimization is now available open-source! 👍 Both the sigmoid (smooth Kendall-tau) and Fenchel-Young (perturbed optimizers) versions. Also, an optimized C++ implementation that is ~40X faster than the Python one. 🤩⚡ github.com/google-deepm...

0163

Reposted by Manfred Diaz

Marc Lanctot @sharky6000.bsky.social · 26/03/2025

Working at the intersection of social choice and learning algorithms? Check out the 2nd Workshop on Social Choice and Learning Algorithms (SCaLA) at @ijcai.bsky.social this summer. Submission deadline: May 9th. I attended last year at AAMAS and loved it! 👍 sites.google.com/corp/view/sc...

sites.google.com

SCaLA-25

A workshop connecting research topics in social choice and learning algorithms.

0196

Manfred Diaz @manfreddiaz.bsky.social · 04/03/2025

Come to understand ML evaluation from first principles! We have put together a great AAMAS tutorial covering statistics, probabilistic models, game theory, and social choice theory. Bonus: a unifying perspective of the problem leveraging decision-theoretic principles! Join us on May 19th!

161

Manfred Diaz @manfreddiaz.bsky.social · 25/02/2025

Elo drives most LLM evaluations, but we often overlook its assumptions, benefits, and limitations. While working on SCO, we wanted to understand the SCO-Elo distinction, so I looked and uncovered some intriguing findings and documented them in these notes. I hope you find them valuable!

021

Reposted by Manfred Diaz

Marc Lanctot @sharky6000.bsky.social · 24/02/2025

Looking for a principled evaluation method for ranking of *general* agents or models, i.e. that get evaluated across a myriad of different tasks? I’m delighted to tell you about our new paper, Soft Condorcet Optimization (SCO) for Ranking of General Agents, to be presented at AAMAS 2025! 🧵 1/N

16517

Manfred Diaz @manfreddiaz.bsky.social · 11/02/2025

Last week, Michael I. Jordan's insightful talk at the AI Action Summit (www.youtube.com/live/W0QLq4q...) reminded us of the meaningful connections between AI, ML, economics, game theory, and mechanism design. But I'd argue the relationship goes deeper—it's profound, historical, and foundational. ⬇️

youtube.com

AI, Science and Society Conference - AI ACTION SUMMIT - DAY 1

YouTube video by IP Paris

180

Reposted by Manfred Diaz

Joel Z Leibo @jzleibo.bsky.social · 16/11/2024

Concordia is a library for generative agent-based modeling that works like a table-top role-playing game. It's open source and model agnostic. Try it today! github.com/google-deepm...

github.com

GitHub - google-deepmind/concordia: A library for generative social simulation

A library for generative social simulation. Contribute to google-deepmind/concordia development by creating an account on GitHub.

06520

Reposted by Manfred Diaz

Marc Lanctot @sharky6000.bsky.social · 15/11/2024

🚨 Petition to get NeurIPS to join Bluesky 🚨 I just wrote the NeurIPS board requesting them to consider joining Bluesky. It took about 2 minutes. I invite you to do the same. neurips.cc/Help/Contact If they changed the name of the conference for the greater good, there's a chance! Please repost!

neurips.cc

Contact

38217

Reposted by Manfred Diaz

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 13/11/2024

Lets get the multi-agent learning community started up here: go.bsky.app/9gsefkW

56212