Reasoning models produce fractals on hard problems; nonlinear dynamics probe their thinking
burny_tech · x · 2026-09-09
The Gilpin lab reports that reasoning models produce fractals when asked to solve hard problems, and that nonlinear dynamics can be used to probe the thinking processes of recurrent-depth models on Sudoku, mathematics, and even ARC-AGI (part 1/N).
The post echoes Jascha Sohl-Dickstein's blog "Neural network training makes beautiful fractals": training and fractal generation share a mechanism—repeatedly applying a parameterized function to its own output—and the hyperparameter boundary between training success and failure has gorgeous fractal structure (paper: arXiv:2402.06184). Together they suggest fractal geometry is pervasive in deep learning dynamics.
More from Research
- Jim Fan declares VLA dead: multimodal coding is the right action space for robotics' System 2 — DrJimFan · 2026-09-09
- Team takes 1st on public leaderboard of PhysAI Dynamic 4D Reconstruction Challenge with Flow4R+ — elliottszwu · 2026-09-09
- The Mathematics Autoformalization Project: translating all known math into formal code — burny_tech · 2026-09-09
- OpenFrontier (RSS 2026): zero-shot open-world robot navigation with VLM-scored frontiers — rsasaki0109 · 2026-09-09
- Open problems turned into RL environments: benchmarks and RL envs are two sides of the same coin — burny_tech · 2026-09-09
- ICML 2026 outstanding paper drama: concurrent diffusion sampling result, only one got the award — peter_richtarik · 2026-09-09