The cost there is multiple rounds of review tokens making it both slow and expensive.

These things are still very far from human-level intelligence. Maybe a touch beyond a golden retriever in processing power. Ratcheting the intelligence up a notch from there is expensive. It’s a lot cheaper to simplify the problem it’s solving instead.

There are many models that are neither slow nor expensive that are suitable for targeted review tasks.

Man-computer symbiosis is the void: mechanically extended man or AI.

Distilling LLMs are a reversal of that.