  My experience with AI in the design context tends to reflect what I think is generally true about AI in the workplace: the smaller the use case, the larger the gain.

This might be the money quote, encapsulating the difference between people who say their work benefits from LLMs and those who don't. Expecting it to one-shot your entire module will leave you disappointed, using it for code completion, generating documentation, and small-scale agentic tasks frees you up from a lot of little trivial distractions.

▲ m463 2 hours ago | parent | next [-]

> frees you up from a lot of little trivial distractions.

I think one huge issue in my life has been: getting started

If AI helps with this, I think it is worth it.

Even if getting started is incorrect, it sparks outrage and an "I'll fix this" momentum.

▲ kulahan 2 hours ago | parent | prev | next [-]

An agentic git interface might be nice, though hallucinations seem like they could create a really messy problem. Still, you could just roll back in that case, I suppose. Anyways, it would be nice to tell it where I'm trying to get to and let it figure out how to get there.

▲ helterskelter 3 hours ago | parent | prev | next [-]

Honestly one the best use cases I've found for it is creating configs. It used to be that I was able to spend a week fiddling around with, say, nvim settings. Now I tell an LLM what I want and it basically gives it to me without having to do trial and error, or locating some obscure comment from 2005 that tells me what I need to know.

	▲	mattmanser 2 hours ago \| parent [-]
		Depends what you're doing. If it's a less trodden path expect it to hallucinate some settings. Also a regular thing I see is that it adds some random other settings without comment and then when you ask it about them it goes, whoops, yeah, those aren't necessary.

▲ awesome_dude 3 hours ago | parent | prev [-]

And bug fixes

"This lump of code is producing this behaviour when I don't want to"

Is a quick way to find/fix bugs (IME)

BUT it requires me to understand the response (sometimes the AI hits the nail on the head, sometimes it says something that makes my brain - that's not it, but now I know exactly what it is