if I’d known that Revolt was using LLM code, I would never have tried to re-engage with the community there.
Gods. The second I saw that Torvalds used an LLM to generate any amount of code I knew people would be annoying as shit about it. And here we are with people being annoying as shit about it.
Maybe you should try to learn what value Torvalds sees in it then and be a little less knee jerk about it
Where in my comment did I mention my stance on LLM usage? All I said was I knew people would be annoying about Torvalds using LLMs to generate code, and that there was an instance of that here.
Yeah, because it’s nuanced and people suck at nuance.
And his take is reasonable, I think. Use it for unimportant shit that would otherwise waste your time.
To me, it makes sense for things that are simple to review, have clear, binary acceptance criteria, and little to no meaningful attack surface or dangerous failure modes. If you are trying to make an AI develop a bulletproof filesystem device driver or network stack you’re a fucking maniac and should be pilloried in the town square. If you want to throw an AI-generated github actions build script at me that’s perfectly fine and once I’ve reviewed it thoroughly it doesn’t bother me one bit if it’s AI-generated.
Next time you need to go the doctor ask your AI instead please.
There was very little LLM-generated code in the first place, AFAIK it was just a couple pieces of build tooling?
So many people in the comments (of the linked site) butthurt over this decision. Ai generated code is just bad, bro. Nobody wants a program coded by someone who doesn’t understand the output.
Well, it’s Hacker News. A place run by Mark Andreesen and has huge incentives, especially on the personal level, to worship AI.
I’m surprised by the comments that are smart enough to push back against the corporate line.
