Simulating cellular automata on an 'LLM computer' to show thinking is computational

ctjlewis · x · 2026-09-28

The author demos running programs on an "LLM computer": busy beaver, Game of Life, and all 256 elementary cellular automata. The core argument: thinking is computational—today's natural-language "reasoning" is the same kind of process with ideas and pure symbols. The accompanying paper shows 99% R accuracy on strawberry with gpt-3.5-turbo using 3 counting examples, necessarily via intermediate counting steps.

Related event: Running cellular automata on an 'LLM computer' to argue thought is computation(2 posts)→

Original post →

More from Research

Research channel →