Post from AI/Chat GPT of Cellular Automata Project - MyCo

 Analysis of myco project from chat gpt.

Yep — that’s the key jump, and you’re absolutely right to call it out.
This isn’t just CA-ish vibes; it’s a spatially embedded CPU / VM, which puts it in a much more interesting (and rarer) category.

Let me frame what myco actually is in the right mental model 👇

What makes myco different from classic cellular automata

Classic Wolfram-style cellular automata:

  • Each cell = passive state

  • Update rule = global, uniform, stateless

  • No memory, no instruction pointer, no branching

  • Complexity emerges, but cells do not compute

In myco:

  • Each grid cell = memory

  • Ants = mobile CPUs

  • Ants execute instruction-level operations

  • Space is not just state — it’s code + data

  • Execution order matters (control flow exists)

That’s a fundamental shift.

You’re no longer in “cellular automata”
You’re in spatial computation.

The correct conceptual bucket: Spatially Distributed Computation

This system sits at the intersection of:

1. Cellular automata

(simple rules → emergence)

2. Turing machines

(read/write tape, instruction pointer)

3. Core War–style systems

(programs living in shared memory)

4. Artificial life

(self-modifying, evolving structures)

In other words:

A CPU whose RAM is a 2D world and whose program counter walks.

That’s rare, and historically very important.

Closest historical relatives (this is the good stuff)

🔹 Langton’s Ant (ancestor)

  • Single agent

  • Reads cell

  • Writes cell

  • Turns + moves

But:

  • No instruction set

  • No branching

  • No arithmetic

  • Not programmable

myco is basically Langton’s Ant with an ISA.

🔹 Turmites (generalized ants)

  • Ant behavior depends on state + cell value

  • Can encode logic

  • Still finite-state, not a CPU

myco goes past this by adding:

  • Registers / state

  • Instruction decoding

  • Writeable memory

🔹 Core War (VERY close cousin)

  • Programs live in shared memory

  • Programs can overwrite each other

  • Execution is decentralized

  • Self-modifying code is normal

Difference:

  • Core War memory is linear

  • myco memory is spatial

  • Execution happens via movement

This makes myco feel more biological.

🔹 Funge languages (Befunge, A fungeoid)

This is probably the closest conceptual match.

  • 2D grid of instructions

  • Instruction pointer moves

  • Code is spatial, not linear

  • Self-modifying programs encouraged

myco is basically:

A stochastic, agent-based Befunge running inside an artificial life simulation

Which is wild.

Why the “CPU per grid” idea matters

This introduces things CA cannot do:

✔ Control flow

  • Conditional execution

  • Loops

  • Divergence

✔ Local computation

  • Different regions compute different things

  • No global clock rule required

✔ Evolutionary pressure

  • Instructions mutate

  • Execution paths change

  • Some “programs” survive longer

✔ Computational universality (likely)

Even if not proven, systems like this almost always drift toward Turing completeness.

This is exactly why Wolfram was obsessed with Rule 110 — but myco skips the elegance and goes straight to raw computational expressiveness.

Why this feels biologically “right”

This mirrors real cells better than CA:

Biologymyco
DNAInstruction grid
RibosomesAnts (executors)
MetabolismCPU ops
MutationRandom writes
EvolutionSurvival of stable instruction loops

Cells don’t update synchronously like CA.
They run asynchronous local computation, just like this.

The big idea hiding underneath

You’re looking at a form of:

Embodied computation

Where:

  • Computation is inseparable from space

  • Programs exist physically

  • Execution has cost (movement)

  • Errors create novelty

This connects directly to:

  • Artificial abiogenesis research

  • Self-replicating code

  • Open-ended evolution (the holy grail)

Most CA don’t get here because they’re too clean.

Why most projects like this fail (and why that’s okay)

Systems like myco often stall because:

  • Too much entropy → everything dies

  • Too little entropy → nothing evolves

  • Instruction set too powerful → chaos

  • Instruction set too weak → stagnation

Tuning this is harder than ML.
It’s closer to ecosystem design.

But when it works, you get:

  • Emergent replication

  • Parasites

  • Arms races

  • Proto-organisms

That’s the dream.

https://github.com/Reconcyl/myco



Comments

Post a Comment

Popular posts from this blog

JVM Notebook: Basic Clojure, Java and JVM Language performance

Image
"Measure, don't guess. The primary goal of all performance tuning exercises should be maximize the end user experience given the resource constraints." [1] "It isn't so much a "farewell to the J" as an expansion of the platform opportunities Java provides. Sun's investment to power ongoing development of JRuby and Jython broadens the range and reach of Java, as a whole." -- Rick Ross Overview and JVM Languages    One of the exciting trends to recently emerge from the Java community is the concept of the JVM language. These technologies are all that you would expect them to be. They are implementations of languages that run on the Java Virtual Machine. Some are newly created and some are based on existing, more mature languages. JRuby, Jython are two JVM languages based on CRuby and CPython. Groovy, Scala, Clojure are three completely new JVM languages that were created to add new language features that weren't supported by the core Ja...
Read more

On Unit Testing, Java TDD for developers to write

It has been a while, let's kick off 2017 with a blog entry. I have read and I am reading about four or five posts a day about unit testing. It really has been a long time obsession for me. I have moved past the technical and practical considerations on unit testing frameworks and done with the debates with "should you use Junit or Mockito or Karma?" I am more interested in the psychology of unit testing, who does it, likes it, hates it? It really is one of those easy to learn, hard to master concepts. For example, many many may play chess when they are young and can end up being horribly chess players most of their life, I am part of that majority. Unfortunately, I have never played chess and sat down for hours and tried to master it. I never see the common patterns or have a developed end game. I mostly just play with a knowledge of the basic rules. Following good unit testing practices within your software development shop is a lot like playing chess. It is easy to le...
Read more

Application server performance testing, includes Django, ErlyWeb, Rails and others

Image
The following represents a set of toy benchmark results for various web application servers including ErlyWeb, Hunchentoot, Django and other application servers. The goal was to test out of the box performance through a simple VIEW page. For example, I was trying to avoid static files but going through the controller and the view. In the Rails example, there is a simple controller that then activates the view template. The same approach is used with the ErlyWeb example. Ideally, we are trying to avoid the server loading the static files but in our case the server may be loading cached content. Overall, Erlang's ErlyWeb/Yaws had great performance and out of the box Django did very well. Tomcat and my various low-level simple JSP/Servlet apps also had stable performance. Software and Hardware Configuration used in the Benchmark Two machines were used in the benchmark, a Win32 dual core machine and a single CPU Linux machine. Win32 Box: Microsoft Windows XP, Vers 2002, Service ...
Read more