Nice video discussing the recent thought-provoking paper: “Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis” arxiv.org/abs/2505.11581 By Akarsh Kumar Jeff Clune Joel Lehman Kenneth Stanley 15min Machine Learning Street Talk video↓

This is a really great video! Ken summarizes things extremely well, Akarsh makes great points, and everything is well summarized by Tim. Great work Machine Learning Street Talk !!

I've read most of the collective works of the QD trio Kenneth Stanley - Jeff Clune - Joel Lehman , and yet this Machine Learning Street Talk video really hits differently - incisively cutting to that nagging feeling we all have when using (incredible!) LLMs today

Thrilled to introduce Foundation Model Self-Play, led by Aaron Dharna. FMSPs combine the intelligence & code generation of foundation models with the curriculum of self-play & principles of open-endedness to explore diverse strategies in multi-agent games, like the one below 🧵👇

I'm really excited to be presenting FMSPs at RL_Conference later this year!

a guy created a dataset of 50 books from London 1800-1850 for LLM training. no modern bias. it’s actually super cool to see what can be trained on it!

Generative models are great at mimicking data — but real (scientific) discovery requires going beyond it. Excited to present our paper “Provable Maximum Entropy Manifold Exploration via Diffusion Models” this Wednesday at ICML 2025! We propose a scalable, theoretically grounded

I worry that so much discussion of AI risks and alignment overlooks the rather large elephant in the room: creativity and open-endedness. Policy makers and gatekeepers need to understand two competing forces that no one seems to talk about: (1) there is a massive economic

Whatever we build is driven by some philosophy, whether examined or not. This is why I'm a fan of @cosmos_ins's call for philosopher-builders (link below). The future isn't fixed, what we choose to build -- and why -- matters. It's worth examining our OS to check for upgrades.

"When does Neuro-evolution out-compete Reinforcement Learning in Transfer Learning tasks?" Find us at GECCO 2025 where we are presenting this work of our Grow-AI team with Sebastian Risi Milton Joachim Winther Pedersen erwan plantec arxiv.org/abs/2505.22696 sebastianrisi.com/grow-ai/

Could not be more excited about teaming up with Joel Simon ! Welcome, Joel, to the Lila Open-Endedness Team!

Sounds like a potential side effect of fractured entangled representation (FER) from SGD under conventional conditions. See arxiv.org/abs/2505.11581

We’re training AI on everything that we know, but what about things that we don’t know? At #ICML2025, the EXAIT Workshop sparked a crucial conversation: as AI systems grow more powerful, they're relying less on genuine exploration and more on curated human data. This shortcut

"Why Greatness Cannot Be Planned" Japanese edition! Kenneth Stanley Joel Lehman

Amazing to see a Japanese edition of the book “Why Greatness Cannot Be Planned” by Kenneth Stanley and Joel Lehman now available in Japan! 🇯🇵⛩️ Thanks Mizuki Oka/岡瑞起 鈴木 健 and others for working on this project.

A great honor to have our book Why Greatness Cannot Be Planned debut as a brand new Japanese edition! Thank you Sakana AI for calling it out! Joel Lehman and I are thrilled to share our ideas with Japan, and special thanks to the tireless efforts of Mizuki Oka/岡瑞起 and 鈴木 健