Reasoning models produce fractals on hard problems, probed via nonlinear dynamics
ayushthakur0 · x · 2026-09-09
Researchers found that reasoning models produce fractal structures when solving hard problems. Using nonlinear dynamics, they probe the thinking processes of recurrent-depth models on Sudoku, mathematics, and even ARC-AGI, offering a new lens into internal reasoning computation.
Related event: Fractal basins and transient chaos explain why reasoning models overthink(13 posts)→
More from Models
- Dwarkesh on MagicAILabs' 50x compute claim: RSI may be less compute-bottlenecked than we think — AccBalanced · 2026-09-09
- Rumor: OpenAI may have cracked Navier-Stokes, with human mathematicians laying years of groundwork — LucaAmb · 2026-09-09
- '50% of open problems just solved' — commentator marvels at frontier model progress — BorisMPower · 2026-09-09
- Cheap models via OpenRouter fall apart in agentic harnesses: GLM and DeepSeek can't match Claude — scottyLogJobs · 2026-09-09
- COLM 2026 paper: recent claims that LLMs can introspect don't meet the evidentiary bar — tallinzen · 2026-09-09
- Skeptic Dismisses OpenAI's Navier-Stokes Claim: 'It's Obviously in the Training Set' — adonis_singh · 2026-09-09