Comment by embedding-shape

> That's a totally separate thing from LLMs. We are constantly told that if we learn the magic way to use LLMs, we can spit out functioning code a lot faster. But in reality, people are just generating code faster than they can verify it.

I don't see it as it is. LLMs are not magically gonna make you be able to produce high-quality software, just like Ableton isn't gonna magically gonna make you be able to produce high-quality music. But if you learn the tool, it gets a lot easier to use effectively. And the better you are at "producing high quality music/code", probably the more use you can make of Ableton/LLMs, compared to someone who aren't good at those things already.

Again, what you're being told by other people, I don't know, and frankly don't really care. OpenAI sold Codex to me as a tool that can help me, a programmer, do programming, and that's exactly what that tool gives me.

Cursor in their article tried to sell their tool as something that can "Hundreds of agents can work together on a single codebase for weeks, making real progress on ambitious projects" which I claim in TFA, doesn't seem to be true.