AI agents iteratively optimize Rust code to achieve 2x-20x speedups over state-of-the-art libraries through repeated prompting and benchmark-driven improvements.

Writing Rust code that's faster than state-of-the-art libraries by asking agents to make the code faster

In January 2025, I had a fun hypothesis for a blog post: can LLMs write better code if you keep asking them to “write better code”? That was prior to the advent of robust agentic coding, but Claude Sonnet 3.5 was still able to iteratively improve on algorithmic Python code. The “better” instruction turned out to be underspecified: Sonnet abused that ambiguity to instead add a ton of useless features but the code was indeed faster. Even with the rise of agentic LLMs specifically RLHFed to handle ...