Delegation vs Review: You Can Only Hand Off What You Can Verify

Sat, 26 Sep 2026 00:00:00 +0000

AI now writes code and finds bugs faster than people can carefully read. Once line-by-line review stops being possible, what can we still trust? And where does that trust end?

My current answer: what you can safely hand to AI depends on what a human can verify. What changes is what the human verifies. We used to read the code. Now we mostly look at the machinery that produced the result: the verifier says “proof checks”, the sandbox says “can’t get out”, the sampling audit says “distribution looks normal”. Those are the things we trust. They deserve that trust because the mechanisms behind them are small and rarely change, so a person can check them once and keep relying on them. This post tries to answer two questions: which properties can be handed to mechanisms like that, and what to do when a mechanism itself fails.

AI on Hongbo Chen

Delegation vs Review: You Can Only Hand Off What You Can Verify