Writing Rust code that's fast by asking agents to make the code faster

Automated excerpt

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”? Use diverse datasets with different matrix sizes than the benchmarks. These subagents MUST use `gpt-5. 6-luna` in Codex, e. g.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.