Our readingWhat is a korrent?
Agent-written code that runs and passes its tests is not enough: security, maintainability and being able to roll it back still need humans in the loop.
Drawn from what Tony Fadell said
What this subject means
software quality Whether a program is any good and how anyone would know: tests, review, debt, and what a suite cannot cover.
Mental modelMargin of safety
On the topicWhat are tests for, and how much testing is enough?under our view: Tests an agent wrote cannot be trusted on their own, so a person still has to check