LearningLukeD's profile picture. Research Scientist at @SakanaAILabs

I build Continuous Thought Machines: https://pub.sakana.ai/ctm/

I research intelligence from the ground up.

Luke Darlow

@LearningLukeD

Research Scientist at @SakanaAILabs I build Continuous Thought Machines: https://pub.sakana.ai/ctm/ I research intelligence from the ground up.

Luke Darlow รีโพสต์แล้ว

Learn more about this approach by reading our technical report by @_ivyzhang @risi1979 @LearningLukeD 👇🏼 pub.sakana.ai/pdnca


Luke Darlow รีโพสต์แล้ว

Now that PD-NCA is public, here's a rough list of directions I'm excited to see NCAs explore (in no particular order):

_ivyzhang's tweet image. Now that PD-NCA is public, here's a rough list of directions I'm excited to see NCAs explore (in no particular order):

Very happy to share our ALife work, where we simulate "digital petri dishes". The goal: to explore the role of learning and intelligence on the formation and complexification of life. The tool: a multi-agent competitive framework, continuously optimized with backprop. Enjoy!

Introducing Petri Dish Neural Cellular Automata (PD-NCA) 🦠 The search for open-ended complexification, a north star of Artificial Life (ALife) simulations, is a question that fascinates us deeply. In this work we explore the role of continual adaptation in ALife simulation,…



Luke Darlow รีโพสต์แล้ว

“Why one AI lab is betting that research freedom beats million-dollar salaries” 💡🧠 venturebeat.com/ai/sakana-ais-…

SakanaAILabs's tweet image. “Why one AI lab is betting that research freedom beats million-dollar salaries” 💡🧠

venturebeat.com/ai/sakana-ais-…

Luke Darlow รีโพสต์แล้ว

Sakana AI’s CTO says he’s ‘absolutely sick’ of transformers, the tech that powers every major AI model “You should only do the research that wouldn’t happen if you weren’t doing it.” (@thisismyhat) 🧠 @YesThisIsLion venturebeat.com/ai/sakana-ais-…


I had to share this stunning gif! Do Continuous Thought Machines dream dream of electric sheep...? This is a UMAP projection showing the neurons of a CTM firing while generating text (5 tokens, with time to think between). Do you see the emergence of FAST and SLOW thoughts?


Luke Darlow รีโพสต์แล้ว

Kicking off #TEDAISF2025 with none other than @YesThisIsLion — Co-Author of “Attention Is All You Need” and CTO/Co-Founder of Sakana AI. His reflections on the evolution of AI architecture and what’s next for intelligence, made for the perfect Session 1 opener. 🚀

TEDAISF's tweet image. Kicking off #TEDAISF2025 with none other than @YesThisIsLion  — Co-Author of “Attention Is All You Need” and CTO/Co-Founder of Sakana AI.

His reflections on the evolution of AI architecture  and what’s next for intelligence, made for the perfect Session 1 opener. 🚀
TEDAISF's tweet image. Kicking off #TEDAISF2025 with none other than @YesThisIsLion  — Co-Author of “Attention Is All You Need” and CTO/Co-Founder of Sakana AI.

His reflections on the evolution of AI architecture  and what’s next for intelligence, made for the perfect Session 1 opener. 🚀

Petri Dish NCA: some recent fun work with @_ivyzhang and @risi1979, presented at ALife2025. Each colour is it's own species. The simulation is differentiable and learning is continuous. More fun videos and an explanation here: iyzg.github.io/petri-dish-nca/


Luke Darlow รีโพสต์แล้ว

IASC: Interactive Agentic System for ConLangs arxiv.org/abs/2510.07591 If you’re a fan of science fiction or fantasy, you’ve probably heard of made-up languages like Elvish from “The Lord of the Rings” or Klingon from “Star Trek.” Can LLM agents create new artificial languages?…


Luke Darlow รีโพสต์แล้ว

We are excited to share that “Continuous Thought Machines” has been accepted as a Spotlight at #NeurIPS2025! 🧠✨ The CTM is an AI that mimics biological brains by using neural dynamics & synchronization to think over time. It can solve complex mazes by building internal maps,…


Super happy to announce that Continuous Thought Machines has been accepted as a spotlight for NeurIPS2025. We are working on so very many fascinating directions - the CTM architecture just keeps opening doors to fun, thought-provoking projects.

We are excited to share that “Continuous Thought Machines” has been accepted as a Spotlight at #NeurIPS2025! 🧠✨ The CTM is an AI that mimics biological brains by using neural dynamics & synchronization to think over time. It can solve complex mazes by building internal maps,…



Luke Darlow รีโพสต์แล้ว

Cool to see works like AB-MCTS, The AI Scientist and the Darwin Gödel Machine being included in the new “Self-improving AI Agents” course at Stanford! cs329a.stanford.edu

SakanaAILabs's tweet image. Cool to see works like AB-MCTS, The AI Scientist and the Darwin Gödel Machine being included in the new “Self-improving AI Agents” course at Stanford!

cs329a.stanford.edu

Luke Darlow รีโพสต์แล้ว

“Automating the Search for Artificial Life With Foundation Models” is now published in the Artificial Life Journal! 🦎🧠 Article: direct.mit.edu/artl/article/3… ASAL is a method using foundation models to automate the discovery of new artificial lifeforms, accelerating ALIFE research.


Luke Darlow รีโพสต์แล้ว

We are excited to highlight @SakanaAILabs as a Gold Sponsor of #ALIFE2025! @SakanaAILabs is doing groundbreaking work in nature-inspired intelligence, collective models, and automated scientific discovery. Their involvement enriches #ALIFE in multiple ways: ⬇️ x 2

ALifeConf's tweet image. We are excited to highlight @SakanaAILabs as a Gold Sponsor of #ALIFE2025! 

@SakanaAILabs is doing groundbreaking work in nature-inspired intelligence, collective models, and automated scientific discovery. Their involvement enriches #ALIFE in multiple ways:

⬇️ x 2

Luke Darlow รีโพสต์แล้ว

If you’re struggling to understand what people mean when they say things like “truly understand,” it boils down to Unified Factored Representation (UFR). That’s the foundation behind the slippery intuition.

kenneth0stanley's tweet image. If you’re struggling to understand what people mean when they say things like “truly understand,” it boils down to Unified Factored Representation (UFR). That’s the foundation behind the slippery intuition.

A student who truly understands F=ma can solve more novel problems than a Transformer that has memorized every physics textbook ever written.



🗜️Compress is (or at least demonstrates) intelligence🧠 Starting with a picture of me and prompting Gemini with "Create an exact replica of this image, don't change a thing." yields this quite bizarre progression! Does this seem like 🧠 or 😂 to you? This was a fun experiment!


United States เทรนด์

Loading...

Something went wrong.


Something went wrong.