Optimization researcher: with LLMs and domain harnesses, we go 10x faster on harder problems

ErnestRyu · x · 2026-08-19

In a thread, optimization theorist Ernest Ryu described using LLMs for mathematical research, admitting some constructions were "frightening" and that he would not have figured them out without LLMs and a domain-specific harness. He argues that embracing these tools gives optimization theory a very optimistic future: going 10x faster, solving harder and more interesting problems, and having stronger downstream impact on optimization practice.

Related event: LLM-Powered AutoOPT Discovers New Optimization Algorithms(3 posts)→

Original post →

More from Models

Models channel →