Can we finally make a theory for Darwin's "Endless Forms Most Beautiful and Most Wonderful"? Introducing ruliobiology as a path to general theory in biology, starting with foundations for a theory of biological form writings.stephenwolfram.com/…

one elegant post-training method that caught my attention in 2026 is VPO who in a nutshell post-train the models to output diverse set of good answers. in this 2h odyssey we cover: - why diversity is important - a magic trick - reward shaping for exploration - a top tier figure

Can “chicken” make a base model reason? 🐔 Yes! Why? With the right first tokens, base models can match RL in reasoning. We trace this to learned training data associations and use a simple data edit to make “chicken” elicit reasoning too. blog: sophielwang.com/cues

"Evolution is anything but random." This is INSANE... @akarshkumar0101 (@MIT_CSAIL, @SakanaAILabs) on artificial life: searching the space of possible universes with foundation models, why evolved networks find structure SGD misses (with @kenneth0stanley), and LLMs evolving Core War programs.

"Evolution is anything but random." This is INSANE... @akarshkumar0101 (@MIT_CSAIL, @SakanaAILabs) on artificial life: searching the space of possible universes with foundation models, why evolved networks find structure SGD misses (with @kenneth0stanley), and LLMs evolving Core War programs.

Is this machine playing? 🏀🪁🛝 We left Eko, an embodied coding agent, on an island for 30 hours with no task or goal, studying it like ethologists study a new species Eko explored, built, climbed, made games, and learned completely new techniques (1/9) machineplaying.org

Is this machine playing? 🏀🪁🛝 We left Eko, an embodied coding agent, on an island for 30 hours with no task or goal, studying it like ethologists study a new species Eko explored, built, climbed, made games, and learned completely new techniques (1/9) machineplaying.org

(1/7) Humans can acquire many capabilities without (catastrophically) forgetting previous ones. Why can't neural networks do the same? Local Support Learning (LSL) takes us a step closer towards this goal. In LLMs of up to 7B parameters, LSL augments gradient-based training to retain prior capabilities while learning new tasks at full capacity. Notably, it does so without access to prior data. Key idea: casting forgetting as a geometric problem, and optimizing for the worst case. Paper: arxiv.org/abs/2610.02126 Website and code: assafbk.github.io/lsl

X-rays are everywhere in medicine, but extracting general, quantitative anatomical information from them remains remarkably difficult. Announcing FleXray: an open-source, open-weight model for zero-shot anatomical segmentation across the human body—from different regions, viewing angles, and acquisition settings. FleXray learns from large-scale synthetic supervision generated from 3D anatomy, then transfers directly to real clinical X-rays. Try it now on your own X-rays in our in-browser demo! 🧵 1/N — project page, demo, weights, code & paper below ↓

Introducing the Sakana AI Frontier Intelligence Group 🪷 sakana.ai/frontier-intellige… Current AI systems are incredibly capable, but is intelligence “solved”? And if not, what’s missing? At Sakana AI’s Frontier Intelligence Group (FIG), we believe that there are still breakthroughs to be made in AI. The Transformer and language modeling may be incredibly powerful, but it doesn’t mean that better alternatives don’t exist. Natural intelligence still beats artificial intelligence across many dimensions. Agents lack the deep insights and creativity of humans. Individual models require far more data than the brain to learn robustly, and require far more energy to run. If we set these as targets, what kinds of AI systems could we develop? Research at FIG has sought to address the gaps between natural and artificial intelligence. Here are some of our works, and the fundamental research questions that motivated them: • Continuous Thought Machines: How can we improve information processing by leveraging temporal dynamics? • Augmented Lagrangian Predictive Coding: How can local learning solve multilayer credit assignment? • Sparser, Faster, Lighter Transformer Models: How can we massively increase data efficiency and generalization? • The AI Picbreeder Experiment: How can we make artificial open-ended systems? • Smart Cellular Bricks: How can physical systems achieve collective intelligence and self-repair without a central brain? We hope that this encourages other researchers to also explore different paradigms, and take a leap of faith with us. After all, in the words of a dear friend of ours, “greatness cannot be planned”.