Item — HN Reader

> There is no reason to believe that future AI platforms won't be able to review code themselves and manage some aspects of themselves with minimal human oversight

There are, IMHO, fewer reasons to believe they will be able to do that rather than not, though.

1 comments

LLMs became much better at both reviewing and writing code over the last 12-18 months. Did you?

The current state of the art is irrelevant. Only the first couple of time derivatives matter.

> Did you?

I would say I got better at both of those over the last 12-18 months. Are your skills static?

Compared to Claude or GPT 5.5? Yeah, my skills are static relative to the progress seen recently. So are yours, unless your grandpa was named von Neumann or Szilard.

My brain got better at thinking deeper when I stopped using llms.

Lmao why does it seem outlandish to other people? Perhaps they never thought too deeply in the first place to recognise it.