For a split second there I believed there is a new Distill publication! Their articles were the most inspirational and eye-opening resource on my beginnings of ML journey, the quality of visualizations definitely made lasting impact on my mental models of _what is going on_.

My favourite goes definitely to The Building Blocks of Interpretability (https://distill.pub/2018/building-blocks/), those images landed in a lot of my university presentations and the dog made everyone immediately interested ;-)

There is ongoing research on neural cellular automata, as they seem to be a very efficient way to generate pretraining tokens: https://arxiv.org/html/2603.10055v1

This has been shared a few times here. It looks cool but I don't understand the usefulness of this tech. This is likely a demo to show some capability, what that is though I don't understand.