Isn’t this just a roundabout way of saying that people who are skilled at using LLMs will get better results from them than people who aren’t? In other words, LLMs “mirror operator skill” in about the same way as hammers, paintbrushes or any other tool. Hardly a blinding insight.
It's a controversial opinion because both AI optimists and AI pessimists can find room for disagreement with the premise. The optimists think vibe coding is about to be fully automated and humans don't have long, one or two years at best. The pessimists think LLMs don't add much value in the first place. In either case they would disagree with the premise.
Agreed. By HN standards I am a very shitty programmer, and as of a year ago I would have said it takes up about 25% of my time. I pretty much just make demos to display some non-coding research.
I think with the rise of LLMs, my coding time has been cut down by almost half. And I definitely need to bring in help less often. In that sense it has raised my floor, while making the people above me (not necessarily super coders, but still more advanced) less needed.