Nenad Tomasev
@nenadtomasev.bsky.social
Developing AI responsibly. Senior Staff Research Scientist at Google DeepMind. Opinions are my own.
Great work from some of my colleagues, check this out! Such a creative application of generative AI! ♟️ www.chess.com/news/view/ai...
DeepMind's AI Learns To Create Original Chess Puzzles, Praised By GMs
In a new study, researchers from Google DeepMind have created an AI system that is capable of generating creative chess puzzles, some of which impressed experts in chess compositions.
chess.com
Take a sneak peak at The Paradox of the Organism at Google books books.google.com/books?hl=sv&... Don’t forget to pre-order!
The Paradox of the Organism
Leading evolutionary theorists and philosophers come together to understand how organisms persist, even as they’re riddled with internal conflict, from cancer cells to selfish genes.How does a vast me...
books.google.com
Arvid Ågren@arvidagren.bsky.social · last yr.Coming December 16!
Another concept that we explore is that of Mission Economies realized through steerable AI agent markets.
Nenad Tomasev@nenadtomasev.bsky.social · last yr.Happy to share a new preprint: Virtual Agent Economies arxiv.org/abs/2509.10147 where we discuss a number of possible frameworks for establishing steerable agent markets.
One of the concepts that we discuss is that of a hypothetical High-Frequency Negotiation (HFN) framework between Personal AI Assistants, on behalf of their users, and in line with individual preferences.
Nenad Tomasev@nenadtomasev.bsky.social · last yr.Happy to share a new preprint: Virtual Agent Economies arxiv.org/abs/2509.10147 where we discuss a number of possible frameworks for establishing steerable agent markets.
Happy to share a new preprint: Virtual Agent Economies arxiv.org/abs/2509.10147 where we discuss a number of possible frameworks for establishing steerable agent markets.
Virtual Agent Economies
The rapid adoption of autonomous AI agents is giving rise to a new economic layer where agents transact and coordinate at scales and speeds beyond direct human oversight. We propose the "sandbox econo...
arxiv.org
For those with interest in mental health and AI, and in particular on how potentially sensitive data gets collected and used there - there is now a Delphi survey that you can fill out to inform how this gets done, as a part of PARQAIR-MH project (www.parqair.org/home), via: redcap.link/2l91l043
parqair.org
Our work on concept discovery towards bridging the human-AI knowledge gap in AlphaZero has now been published in PNAS. As future AI systems become even more capable, we should be thinking of ways of utilizing them not only to perform tasks, but also to further our own knowledge and understanding.
This was cool: "Gemini 2.5, create a sim that is cross between Jujujajaki networks and cellular automata" Gemini: "What's a Jujujajaki network?" I paste in a paper. Gemini: "Got it, a dynamic network with local search & exploration." Worked in one shot. Me: "Make it nicer" Some cleverness here
An interesting read on self-organizing systems, and how order and disorder may manifest differently at different scales: www.nature.com/articles/s44...
Self-organizing systems: what, how, and why? - npj Complexity
npj Complexity - Self-organizing systems: what, how, and why?
nature.com
Dataset Distillation (2018/2020) They show that it is possible to compress 60,000 MNIST training images into just 10 synthetic distilled images (one per class) and achieve close to original performance with only a few gradient descent steps, given a fixed network initialization.
I'm happy to advertise an upcoming Student Researcher position on my Agent Frontiers team here at the Google DeepMind Foundational Research Unit, aimed for a start date early in the summer (currently listed as late June, but obviously somewhat flexible).
Constrained roads to complex brains - Neural development and brain circuit evolution converged in birds and mammals www.science.org/doi/10.1126/...
Constrained roads to complex brains
Neural development and brain circuit evolution converged in birds and mammals
science.org
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.
Model-free deep RL algorithms like NFSP, PSRO, ESCHER, & R-NaD are tailor-made for games with hidden information (e.g. poker). We performed the largest-ever comparison of these algorithms. We find that they do not outperform generic policy gradient methods, such as PPO. arxiv.org/abs/2502.08938 1/N
Can LLMs be used to discover interpretable models of human and animal behavior?🤔 Turns out: yes! Thrilled to share our latest preprint where we used FunSearch to automatically discover symbolic cognitive models of behavior. 1/12
🙏🙏🙏 See also full set of video lectures at m.youtube.com/playlist?lis...
Algorithmic Game Theory (Stanford CS364A, Fall 2013) - YouTube
Course Web site: http://timroughgarden.org/f13/f13.html (includes lecture notes and homeworks). Course description: Broad survey of topics at the interface o...
m.youtube.com
Guillaume Dalle@gdalle.bsky.social · 2y agoIt's not often that I find a math book *accessible*, but this one by @timroughgarden.bsky.social fits the bill. Not that the content isn't challenging, but the author actually cares about the reader and it shows! Go read it if you're interested in auctions, routing or learning equilibria. #MLSky
No company in the self-driving industry has invested in self-play at scale. I've been dying for someone to finally do this—many others have felt the same. This landmark work finally shows the potential in this approach. This is a challenge to the industry.
Eugene Vinitsky 🍒@eugenevinitsky.bsky.social · 2y agoWe've built a simulated driving agent that we trained on 1.6 billion km of driving with no human data. It is SOTA on every planning benchmark we tried. In self-play, it goes 20 years between collisions.
One of the things that I am most excited about is how we can use AI (and language models in particular) to help us generate new scientific hypotheses and accelerate scientific discovery.
We launched a bunch of Gemini 2.0 models today. Compared to the 1.5 series models, each of the 2.0 models is generally better than the "one size up" model in the 1.5 series. 2.0 Flash & Flash-Lite set new standards in the quality/cost Pareto frontier. More details: blog.google/technology/g...
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 Schultz, DeepMind, Mastering Board Games by External and Internal Planning with Language Models
YouTube video by AI4All
youtube.com
Marc Lanctot@sharky6000.bsky.social · 2y agoSuper 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!
John's talk is now available online! www.youtube.com/watch?v=JyxE...
John Schultz, DeepMind, Mastering Board Games by External and Internal Planning with Language Models
YouTube video by AI4All
youtube.com
Matej Jusup@matejjusup.bsky.social · 2y agoJoin John's talk to get insights on our paper on mastering board games with language models!
Check out the Autonomous Agents for Social Good (AASG) Workshop taking place at #AAMAS 2025! Are you doing research on using autonomous agents or multi-agent systems to address social challenges to make the world a better place? Submission deadline: Feb. 4th. panosd.eu/aasg2025/
Marc Lanctot@sharky6000.bsky.social · 2y agoCheck out the accepted workshops at #AAMAS 2025! Many of the deadlines are soon (end of Jan / start of Feb). Please consider submitting your work to one of them. They were great last year. aamas2025.org/index.php/co... I will highlight individual workshops over the next few days.
For those interested in AI for improving mental health, registrations are still open for the next MEXA hackathon. www.linkedin.com/posts/mexaco...
MEXA on LinkedIn: #mexa #hackathon #mentalhealth #ai #innovation
Have you registered for MEXA's next Virtual Hackathon, 𝙈𝙚𝙣𝙩𝙖𝙡 𝙃𝙚𝙖𝙡𝙩𝙝 𝙖𝙣𝙙 𝘼𝙄: 𝙄𝙣𝙩𝙚𝙧𝙫𝙚𝙣𝙩𝙞𝙤𝙣? Now is the time!⏰ Join us in…
linkedin.com
Join John's talk to get insights on our paper on mastering board games with language models!
A new paper dropped from DeepMind: Deliberation in Latent Space via Differentiable Cache Augmentation The trouble is, it's not very readable. I tried making a thread here, but it got far too long, so it's a blog now: timkellogg.me/blog/2024/12...
Explainer: Latent Space Experts - Tim Kellogg
timkellogg.me
Now also out on Arxiv: www.arxiv.org/abs/2412.12119
Mastering Board Games by External and Internal Planning with Language Models
While large language models perform well on a range of complex tasks (e.g., text generation, question answering, summarization), robust multi-step planning and reasoning remains a considerable challen...
arxiv.org
Nenad Tomasev@nenadtomasev.bsky.social · 2y agoI'm excited to share a new paper: "Mastering Board Games by External and Internal Planning with Language Models" storage.googleapis.com/deepmind-med... (also soon to be up on Arxiv, once it's been processed there)
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! ♟️
An updated intro to reinforcement learning by Kevin Murphy: arxiv.org/abs/2412.05265! Like their books, it covers a lot and is quite up to date with modern approaches. It also is pretty unique in coverage, I don't think a lot of this is synthesized anywhere else yet
Reinforcement Learning: An Overview
This manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement learning and sequential decision making, covering value-based RL, policy-gradient methods, model-based met...
arxiv.org
If you will be at #NeurIPS2024 @neuripsconf.bsky.social and would like to come see our models in action, come say hi 👋 and check out our demo at the GDM booth! Wednesday, Dec. 11th @ 9:30-10:00. Lots of other great things to see as well! Check it out: 👇 deepmind.google/discover/blo...
Marc Lanctot@sharky6000.bsky.social · 2y agoSuper 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!