Luke Darlow

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!

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/

Here's another with a different set of hyper-params. Again, super interesting how the different functional layers of the Continuous Thought Machine tend to occupy different spatial structures. Mostly, though, I'm showing off the fun and useful visualization we've built. Pretty!

My updated Continuous Thought Machine v2's neural activation patterns can be so mesmerizing. This CTM has 4 separate dedicated layers (input, attention, output, and motor control). It turns out that they learn to occupy local spaces in 2D UMAP space, just like... brain regions??

M-Layers! We talk about the spiral problem and how it reveals issues in how NNs currently do things in our MLST interview (youtube.com/watch?v=DtePicx_…). M-Layers actually fit spiral data much better than standard MLPs. Nice.

I just came across this really good summary of @YesThisIsLion and my @MLStreetTalk interview (youtu.be/DtePicx_kFY): theneuron.ai/explainer-artic… Noice.

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?

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-nc…

🗜️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!

Learning where to look, learning what to see. Work on Continuous Thought Machines continues to be exciting! As a teaser, take a look at our approach to "Foveated Active Vision". Check it out 👇 (details in the thread) pub.sakana.ai/ctm