Most of the mentioned issues wouldn't be catched by a test loop unless you have ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		NicoJuicy 3 months ago \| parent \| context \| favorite \| on: AI can code, but it can't build software Most of the mentioned issues wouldn't be catched by a test loop unless you have 100% automated tests (unit tests, ...) Which isn't always plausible ( time ). The AI makes makes different mistakes than humans that are sometimes harder to catch.

simonw 3 months ago [–]

It's a lot more plausible now you can get LLMs to help write those tests in the first place.

NicoJuicy 3 months ago | [–]

Most of these examples build ( shallow test in my LLM on the end of the task ) and produced new edge cases

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact