Neural Particle Automata

AI

neural cellular automata

SHOW HN2026

88points
19comments
#775of 4,366 in 2026
Top 18%of 2026 by points

How HN took it

CuriousMostly questions and neutral comments

1 positive, 5 neutral or asking, 0 mixed, 0 critical, out of 6 comments about the project. Thread score +0.12.

Performance: 1 for, 0 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Regeneration after damage is impressive; users enjoy cutting the lizard demo

    From 2 comments
    • Found it much interesting that i could mess up a pattern enough that it couldn't re-form. Would be fun if selecting a new pattern didn't refresh the image as it is. Although…
      sixeyes on HN
    • This is super cool, great work. Is there a video or demo of the 3D point cloud "gaussian splat" like experiments?
      mattdesl on HN
  • Connects to Michael Levin's work on morphogenesis

    From 2 comments
    • On the outside it looks very similar to what Michael Levin found on electrical communication between living cells. There too, the organism's cells were able to structure and…
      waerhert on HN
    • Agree! This reminded me of a post that tweaked my brain a few months ago :) https://open.substack.com/pub/defenderofthebasic/p/why-does-hell-exist Also reminds me of Dr Michael…
      patcon on HN

Objections

  • Regeneration only works from the egg-like initial condition; switching rules mid-rollout breaks morphology

    From 1 comment
    • Indeed! The system has good regeneration capabilities but it certainly has limits. The particles can only grow reliably if they start from the egg-like initial condition. If we…
      esychology on HN

Requests

  • Demo of 3D point cloud gaussian splat experiments

    From 1 comment
    • This is super cool, great work. Is there a video or demo of the 3D point cloud "gaussian splat" like experiments?
      mattdesl on HN
  • Keep the previous pattern visible when selecting a new one instead of refreshing

    From 1 comment
    • Found it much interesting that i could mess up a pattern enough that it couldn't re-form. Would be fun if selecting a new pattern didn't refresh the image as it is. Although…
      sixeyes on HN
  • Support for cell division

    From 1 comment
    • Super cool work!!! Do you think it would be possible to do something like cell division here?
      afrodisiac on HN

Questions

  • How does this relate to cells2pixels NCA work?

    From 1 comment
  • Could it be used for texture synthesis?

    From 1 comment
    • could something similar be used for texture synthesis ? of course the particles will need to be arranged in a grid and everything, or maybe recreate the texture by interpolating…
      Jgoauh on HN
  • Why are cellular automata suddenly everywhere?

    From 1 comment
    • Can someone tell me why cellular automata are suddenly everywhere? I've seen ~10 articles regarding them in the last month.
      skimmed on HN

Alternatives named

  • Neural cellular automata on grids (cells2pixels, distill self-organizing textures)

    From 2 comments
    • How does this relate to https://cells2pixels.github.io/ ?
      meta-level on HN
    • From the original research - self-organizing textures: https://distill.pub/selforg/2021/textures/
      sva_ on HN
  • Michael Levin's bioelectric morphogenesis work

    From 1 comment
    • On the outside it looks very similar to what Michael Levin found on electrical communication between living cells. There too, the organism's cells were able to structure and…
      waerhert on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/48642030)