So run the LLM in an agent loop: give it a benchmarking tool, let it edit the configuration and tell it to tweak the settings and measure and see how much if a performance improvement it can get.

That's what you'd do by hand if you were optimizing, so save some time and point Claude Code or Codex CLI or GitHub Copilot at it and see what happens.

“We will take all the strokes off Jerry's game when we kill him.” - the LLM, probably.

Just like Mr Meeseeks, it’s only a matter of time before it realizes that deleting all the data will make the DB lightning fast.

How much that would cost?