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.
More from Research
- Continual-ARC: lifelong ARC-AGI stream finds agent harness persistence rarely beats simple caching — unifyai · 2026-11-16
- DySENSE: MIT's GenAI framework synthesizes satellite imagery with dynamic city energy maps — MIT · 2026-11-16
- WebArena-Pro: a 300-task multimodal benchmark across 20 self-hosted apps for web agents — McGill-NLP · 2026-11-16
- Training-free page-sparse decode in llama.cpp: 1.72× faster 128k decoding on an RTX 5090 — topppggg · 2026-11-16
- Training Qwen3-8B to drive a simulated hand spawns a dedicated internal 'pressure' direction — repligate · 2026-11-16
- Google Research open-sources PaperOrchestra, a multi-agent framework for writing AI papers — google-research · 2026-11-16