[yorwba]

The article says "our NCA model contains 16 channels. The first three are visible RGB channels and the rest we treat as latent channels which are visible to adjacent cells during update steps, but excluded from loss functions."

[eyvindn]

Thanks for noticing. This is a typo stemming from early experiments. We started out with 16 channels, but switched to 12 channels of state when this worked just as well. I've submitted a correction.