Transient chaos may be an inevitable cost of training models to solve hard problems

wgilpin0 · x · 2026-09-09

Author William Gilpin expands on the paper's practical implications: reasoning models commonly 'overthink' — two similar prompts can yield reasoning traces differing 10x in length and thus token cost. The team speculates that transient chaos is inevitable when training models to solve hard problems: sensitivity is needed to support hard computations, but the tradeoff is unpredictable inference cost.

Related event: Fractal basins and transient chaos explain why reasoning models overthink(13 posts)→

Original post →

More from Research

Research channel →