Profile avatar
sharky6000.bsky.social
Research Scientist at Google DeepMind, interested in multiagent reinforcement learning, game theory, games, and search/planning. Lover of Linux 🐧, coffee ☕, and retro gaming. Big fan of open-source. #gohabsgo 🇨🇦 For more info: https://linktr.ee/sharky6000
711 posts 7,423 followers 351 following
Regular Contributor
Active Commenter
Posts 15 Comments 35

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

submitted 5 hours ago • 1 comment

We are hiring on the Generative Media team in London: boards.greenhouse.io/deepmind/job... We work on Imagen, Veo, Lyria and all that good stuff. Come work with us! If you're interested, apply before Feb 28.

submitted 3 days ago • 5 comments

We have a massive academic base on Bluesky, we can lobby unis to quit X. The French are leading on this, others can do it too. 3 more French unis quit Twitter: Université Paris-Saclay @univparissaclay.bsky.social Université PSL @psl-univ.bsky.social Sorbonne Université @sorbonne-universite.fr

submitted 3 days ago • 7 comments

Here is a (poorly advertised!) postdoctoral role at CMU: the SCS Mark Stehlik Postdoctoral Teaching Fellowship. Still active and someone with interests in AI+teaching would address needs on our side. Applying by end of March should be early enough. apply.interfolio.com/124667

submitted 2 days ago • 0 comments

Looking for a small or medium sized VLM? PaliGemma 2 spans more than 150x of compute! Not sure yet if you want to invest the time 🪄finetuning🪄 on your data? Give it a try with our ready-to-use "mix" checkpoints: 🤗 huggingface.co/blog/paligem... 🎤 developers.googleblog.com/en/introduci...

submitted 5 days ago • 0 comments

www.bbc.com/news/article... "A complex problem that took microbiologists a decade to get to the bottom of has been solved in just two days by a new artificial intelligence (AI) tool." (Google AI co-scientist) What an amazing use of AI! 🤯🤩🎉

submitted 4 days ago • 1 comment

Google's AI co-scientist AI co-scientist, a multi-agent AI system built with Gemini as a virtual scientific collaborator to help scientists generate novel hypotheses and research proposals, and to accelerate the clock speed of scientific and biomedical discoveries. research.google/blog/acceler...

submitted 5 days ago • 1 comment

More introductory resources for e-values from one of the authors of the overview paper I learned about them from. "A Tutorial on Safe Anytime-Valid Inference: Practical Maximally Flexible Sampling Designs for Experiments Based on e-Values" by Ly et al. Thanks @petergrunwald.bsky.social !

submitted 4 days ago • 0 comments

Three large UK universities leave X. This is huge! Which will be the first US university to make the bold first move? Help us make history. 🫵 (Have any Canadian universities left X yet?)

submitted 5 days ago • 0 comments

Curious about the history of Theranos? Check out The Dropout: en.m.wikipedia.org/wiki/The_Dro... The acting is top-notch. It is eerie and gripping. I am only halfway through but the number of times I've said "that can't possibly be true" and turned out to be true.. is mind-boggling. What a story!

submitted 5 days ago • 1 comment

My dad bought an IMSAI 8080 kit computer when I was 9 (~2 years before the Apple II came out). Although it was satisfying entering 8 bits of info one toggle switch at a time, productivity improved considerably once we got an actual keyboard! (Then I could type in BASIC games from Ahl's book)

submitted 6 days ago • 3 comments

A large group of us (spearheaded by Denizalp Goktas) have put out a position paper on paths towards foundation models for strategic decision-making. Language models still lack these capabilities so we'll need to build them: hal.science/hal-04925309...

submitted 6 days ago • 2 comments

[🧵1/N] Please check out our new paper (arxiv.org/abs/2502.11645) on game-theoretic evaluation. It is the first method that results in clone-invariant ratings in N-player, general-sum interactions. Co-authors: @liusiqi.bsky.social , Ian Gemp, Georgios Piliouras, @sharky6000.bsky.social 🎉

submitted 6 days ago • 2 comments

If this subject interests you, I was pointed to a whole book on the subject! 🤩 bsky.app/profile/rdeh... Thanks @wzuidema.bsky.social !

submitted 7 days ago • 1 comment

Aaditya Ramdas and Ruodu Wang wrote an introduction to hypothesis testing with e-values. arxiv.org/abs/2410.23614 The book is organised into three parts: Fundamental Concepts, Core Ideas, and Advanced Topics. It's a very exciting area of research and this is a great starting point for new people!

submitted 101 days ago • 0 comments