Reasoning models produce fractals on hard problems, researchers find via nonlinear dynamics
Stefania_druga · x · 2026-09-10
Gilpin's group discovered that reasoning models produce fractals when asked to solve hard problems, enabling nonlinear dynamics to probe the thinking processes of recurrent-depth models on Sudoku, mathematics, and even ARC-AGI.
BertChakovsky adds that fractal maps appear everywhere in complex systems—from the Mandelbrot set to Lenia to AI models: wherever stable "solutions" exist inside a system, chaotic non-solutions cluster nearby.
More from Research
- Token Collapse: Study Finds Graph Soft Prompting Tokens in LLMs Fail to Encode Structure — Sapienza · 2026-10-27
- Mathathon 2.0 launches with Terence Tao's SAIR, $1.5M in compute for teams — _sathvikr · 2026-10-27
- The 'sweet lesson' is real: two kinds of ML problems need opposite strategies — mike64_t · 2026-10-27
- PixGR: Pixel-space generative decoding for fast feed-forward 3D reconstruction — kwangmoo_yi · 2026-10-27
- UniAction: unified action conditioning lets one world model handle mixed action types — ZeYanjie · 2026-10-27
- Infini-AI Lab open-sources Hermit, a framework for agent harness evolution and continual learning — BeidiChen · 2026-10-27