Are you sure you would know if it didn't work? I use Claude extensively myself, so I'm not saying this from a "hater" angle, but I had 2 people last week who believe themselves to be in your shoes send me pull requests which made absolutely no sense in the context of the codebase.

▲

therealdrag0 5 hours ago | parent [-]

That’s always been the case, AI or not.

	▲	Jweb_Guru 3 hours ago \| parent \| next [-]
		No, it hasn't. I did not have a problem before AI with people sending in gigantic pull requests that made absolutely no sense, and justifying them with generated responses that they clearly did not understand. This is not a thing that used to happen. That's not to say people wouldn't have done it if it were possible, but there was a barrier to submitting a pull request that no longer exists.
	▲	windexh8er 3 hours ago \| parent \| prev \| next [-]
		It just happens to be a lot worse now. Confidence through ignorance has come into the spotlight with the commoditization of LLMs.
	▲	viccis 2 hours ago \| parent \| prev [-]
		In my experience, the people sending me garbage PRs with Claude are the same ones who wrote garbage code beforehand. Now there's just 10x more of it.