Research Scientist at @SakanaAILabs
I build Continuous Thought Machines: https://t.co/6Nbme8J44r
I research intelligence from the ground up.lukedarlow.github.io Tokyo, JapanJoined May 2025
@hive_echo@jeffreyseely If I understand the issue correctly (which is a sizeble caveat, but perhaps @jeffreyseely can elucidate further), it isn't a question of maybes, but more of certainties, simply owing to causality.
The full Transformer vs Post-Transformer debate is live.
80 minutes. Seven rounds. No slides. Real disagreement.
@lukaszkaiser came to defend the Transformer. @adrian_pathway, @YesThisIsLion, and @mlech26l made the case for what comes next.
00:00 Contenders enter the ring
06:30
@MLStreetTalk Interesting take. Your point on AI creating more complexity resonates with me because of What I Do (build funky ML models). Being able to push the envelope of complexity owing to AI tools really opens up some new doors for me.
We are honored to be featured in the latest @twominutepapers video!
You all can watch the full video here:
youtu.be/QzZ4VwDHAT4
Here’s a short clip from it:
What happens when you put competing neural networks in a Petri Dish and start changing the rules while they adapt?
Last year we released Petri Dish NCA, where neural nets are the organisms that learn during simulation. Today we're releasing Digital Ecosystems: a browser-based
@bytecrafter_1@SakanaAILabs Sensitivity to rules is far higher. Try it for yourself. Hitting "reset" resets the models randomly with a different seed. You'll note that there is some sensitivity to seed, but stability in the system is more rule-dependent.
@leo_os8@SakanaAILabs It certainly works as a tool for intuitively understanding how things like optimisers and learning rates function,.
There are so many advances and updates you can make to this (for example, pitting optimisers against one another) that I never got to. Its open source, though...
@SakanaAILabs Sometimes the most fascinating science happens by accident. I was changing (and breaking..) something in the simulation a few days ago, accidentally stumbling across a different simulation landscape.
In my opinion, one of the most diverse and interesting yet. So mesmerizing!
@leo_os8@SakanaAILabs Exactly. But the most powerful thing I learned when building it was that real-time changes to these hyper parameters let's you navigate to edge of chaos regimes, and that's where the interesting stuff happens. It's impossible to get there with hyper parameter search alone.
Super happy to share my new research! I've been building out this web demo purely for the sake of understanding how the system works, but I thought I'd share it with the world. Enjoy!
What happens when you put competing neural networks in a Petri Dish and start changing the rules while they adapt?
Last year we released Petri Dish NCA, where neural nets are the organisms that learn during simulation. Today we're releasing Digital Ecosystems: a browser-based
What happens when you put competing neural networks in a Petri Dish and start changing the rules while they adapt?
Last year we released Petri Dish NCA, where neural nets are the organisms that learn during simulation. Today we're releasing Digital Ecosystems: a browser-based platform for interactive artificial life research.
The setup: several small CNNs share a 2D grid, each seeing only a 3x3 neighborhood. No global plan. They compete for territory by attacking neighbours and defending against incoming attacks, learning via gradient descent online while the simulation runs.
What we didn't expect was the role of the learning itself. Gradient descent isn't just optimising each species' strategy. Instead, it acts to stabilize the whole system during simulation. Species that overextend get pushed back by the loss. Species that stagnate get nudged to grow. This means you can push parameters toward edge-of-chaos regimes: a zone characterised by emergent complexity. Letting the neural networks learn acts to hold the complex system together while you explore and interact.
The platform lets you steer all of this interactively. You can draw walls to create niches, erase parts of the system online, and tune 40+ system parameters to explore the most interesting configurations. We find it mesmerizing to watch species carve out territories and reorganise when you perturb them.
Everything runs client-side in your browser, no install needed.
Blog: pub.sakana.ai/digital-ecosys…
Code: github.com/SakanaAI/digit…
This is some very cool work that builds on our original Petri Dish NCA (pub.sakana.ai/pdnca), using population-based meta optimization to enrich the complexity of the system.
Their paper and website are both very excellent: pbt-nca.github.io
Whereas before it wouldn't be unheard of for me to "understanding while coding". Several months ago I was convinced that part of my design and articulation process was enveloped in the actual coding.
I think I was wrong.
Conversations about the impact of agentic work on humans is largely doomerist, and I dislike that.
An unexpected positive is that I'm now required to design, think deeply, and articulate clearly what I want a system to do. This feels a lot like studying and learning.
"That feeling" of typing out a plan prompt for Claude that you couldn't fall asleep with last night because it was rattling around in your head.
Several paragraphs, many enumerations, verbose instructions.
Finally hitting enter and sipping on coffee feels so much like sci-fi.
6K Followers 2K FollowingFounder of @cognee_ the original OSS Agent memory platform. Econ + Psychologist by training. Solo-bootstrapped → backed by Pebblebed. Berlin. https://t.co/1HTK5ti0T4
758 Followers 395 FollowingPost Training @ Thinking Machines
Previously: Jane Street, Microsoft AI, Keras, Google, UCSD.
Creator of https://t.co/NePjhvJQRQ, https://t.co/CqRs7Wa1MW, and more.
207 Followers 1K FollowingFighting fraud one step at a time ⚡ | Exposing scams | Sharing tips to stay safe online & offline | Knowledge is your best defense 🚫💻📱
422 Followers 506 FollowingAI PhD-ing @aims_oxford, SR @GoogleDeepMind, ex RS @JPMorgan AI, EE with Great Distinction @nyuniversity, Comedian at times, Tiramisu enthusiast
197 Followers 525 FollowingResearcher at VUMC in the Ruderfer lab/Center for Digital Genomic Medicine. Predicting disease with EHR data and genetic information. Lots of ML. CS@mcgillu
6K Followers 6K FollowingFOLLOWS 🫵 https://t.co/F7MzDOU9QS
ML/AI R&D sci/eng, QT, noisy ASR, TTS.
Open ASI+compute for */acc 🚀
It's more fun to compute 😇
Love is wise, hate is foolish 🥰
422 Followers 506 FollowingAI PhD-ing @aims_oxford, SR @GoogleDeepMind, ex RS @JPMorgan AI, EE with Great Distinction @nyuniversity, Comedian at times, Tiramisu enthusiast
1.4M Followers 2 FollowingClaude is an AI assistant built by @anthropicai to be safe, accurate, and secure. Talk to Claude on https://t.co/ZhTwG8d1e5 or download the app.
16K Followers 5K Followingaward winning ai researcher (2 so far) | just graduated cs phd | author how to build conscious machines | musician | @bennettsrazor | i do not work @AnthropicAI
1.1M Followers 172 FollowingNobel Laureate. Co-Founder & CEO @GoogleDeepMind - working on AGI. Solving disease @IsomorphicLabs. Trying to understand the fundamental nature of reality.
30K Followers 361 FollowingAuthor of the book Hands-On #MachineLearning with #ScikitLearn, #Keras and #TensorFlow. Former PM of #YouTube video classification. Founder of telco operator.
6K Followers 235 FollowingAI Researcher: From theory to practice (and back)
Postdoc @MetaAI with @ylecun
PhD @RiceUniversity with @rbaraniuk
Masters @ENS_Ulm @Paris_Sorbonne
2K Followers 706 FollowingEthical AI & Artificial Life • Director @CrossLabsTokyo | President @alifeofficial | Lecturer UTokyo • Open-Ended Cognition | Moral Machines | Future of Minds
6K Followers 615 FollowingThis is my hat, there are many like it, but this one is mine.
Faculty @ UCSF
ex: @MIT_CSAIL 🧢 @berkeley_ai 🎓 Google B̶r̶a̶i̶n̶ DeepMind 🎩
13K Followers 513 FollowingCTO of Technology & Society @Google, working on fundamental AI research and exploring the nature and origins of intelligence. Order "What Is Intelligence?" ⬇️
20K Followers 2K FollowingMad Scientist, DeepDream creator. Designing Self-Organising Systems and Programmable Artificial Life. https://t.co/rntipHzHW3
4K Followers 935 FollowingThe Official X Account of ALIFE Conferences.
The 2026 Conference on Artificial Life - Waterloo (Canada), 17-21 August #ALIFE2026
24K Followers 33 FollowingOfficial account for the visa branch of U.S. Embassy Tokyo. アメリカ大使館ビザ課公式アカウントです。米国ビザに関する最新情報や申請に役に立つ情報を発信します。Terms of Use: https://t.co/ZsDLBK5NlB