We also made a free, open-access edition of the book: http://
neuroevolutionbook.com
@hardmaru
-

Free open-access edition of neuroevolution book now available
By
–
-
MIT Press Book on Neuroevolution and AI Agent Design
By
–
Excited to announce our MIT Press book “Neuroevolution: Harnessing Creativity in AI Agent Design” by Sebastian Risi (@risi1979), Yujin Tang (@yujin_tang), Risto Miikkulainen, and myself.
— hardmaru (@hardmaru) 20 novembre 2025
We explore decades of work on evolving intelligent agents and shows how neuroevolution can… pic.twitter.com/9lKXnyzkCEExcited to announce our MIT Press book “Neuroevolution: Harnessing Creativity in AI Agent Design” by Sebastian Risi (
@risi1979
), Yujin Tang (
@yujin_tang
), Risto Miikkulainen, and myself. We explore decades of work on evolving intelligent agents and shows how neuroevolution can -

Sakana AI Hiring Cloud Backend Software Engineer
By
–
We’re looking to hire a Software Engineer (Cloud Backend Engineer) to help work on Sakana AI’s advanced AI-driven discovery platform.
-
US Government Should Subsidize Open AI Over OpenAI
By
–
The US government should subsidize Open AI rather than OpenAI
-
Sakana AI Receives Executive Award from Zaikai Institute
By
–
We are deeply honored to receive the "Executive Award" from Zaikai Institute. Sakana AI remains committed to fully leveraging the entire team's efforts in building AI foundational technologies to strengthen Japan's industries. We sincerely thank everyone for their continued support.
-
Multi-Agent Neural Cellular Automata Develop Complex Emergent Behaviors
By
–
Excited to release our new work: Petri Dish Neural Cellular Automatahttps://t.co/4mWwFOnbYl
— hardmaru (@hardmaru) 5 novembre 2025
We investigate how multi-agent NCAs can develop into artificial life 🦠 exhibiting complex, emergent behaviors like cyclic dynamics, territorial defense, and spontaneous cooperation! https://t.co/Wjp6KkurSQExcited to release our new work: Petri Dish Neural Cellular Automata https://
pub.sakana.ai/pdnca We investigate how multi-agent NCAs can develop into artificial life exhibiting complex, emergent behaviors like cyclic dynamics, territorial defense, and spontaneous cooperation! -

Another example: MiniMax-M2
By
–
Another example: MiniMax-M2 https://github.com/MiniMax-AI/MiniMax-M2
… -
MLStreetTalk and team attend ALife Conference in Kyoto
By
–
It’s great to see @MLStreetTalk and @blaiseaguera & team in Kyoto for @ALifeConf !
-

Open vs Closed Models: Gap Narrowing, Focus Shifts to Applications
By
–
The gap between open and closed models are narrowing and I expect this trend to continue. As foundation models become commoditized on a global level, the most interesting directions from both research and commercial is not in their development but in finding new ways to use them!
-
Evolution Strategies at Scale Outperforms PPO for LLM Fine-Tuning
By
–
Evolution Strategies can be applied at scale to fine-tune LLMs, and outperforms PPO and GRPO in many model settings!
— hardmaru (@hardmaru) 7 octobre 2025
Fantastic paper “Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning” by @yule_gan, Risto Miikkulainen and team.https://t.co/CEyX6Z5ulG https://t.co/mPkXABJcQzEvolution Strategies can be applied at scale to fine-tune LLMs, and outperforms PPO and GRPO in many model settings! Fantastic paper “Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning” by @yule_gan
, Risto Miikkulainen and team. https://
arxiv.org/abs/2509.24372