Hacker News new | past | comments | ask | show | jobs | submit
I've found that the way I strike a balance is to:

1: Carefully pick critical areas that I do by hand, and have AI do the other 90%.

2: Make small changes by hand before / after doing the work with AI.

Most important: Slowly rotate the areas that I do by hand. This way, I keep my hands-on knowledge good enough to give AI knowledgeable instructions.

I wonder if we are in the "negotiation" stage of grief now. Negotiating how much we can still do with our own brains, rather than completely outsourcing it all.

I am saddened the emergent "fully-agentic" meta that wants to reduce the human programmer to a purely verification role. I do not want to be a QA tester for an LLM. I want to think/understand/control the code myself, even if I no longer write every line by hand. I want to retain my own agency (no pun intended).

This is all so depressing. I still use AI as a pair-programmer. I tell it what to code, and I hammer it until it gives me exactly what I want. So I am stuck in 2024-2025, I guess.

Though, I have been a lot more liberal with code I do not care as much about. I have mostly stopped making comments on my coworker's PRs... The code their AI writes looks unfamiliar, but there are no obvious errors, and it feels pointless blocking a PR over minor issues (ex: "hey this fn already exists in utils module", "hey, we do not annotate fn returns, because type checker infers automatically", "hey, you abstracted 2 lines of code into its own fn, but you only use it one place, so just inline it"). Haha, at least, I am not standing in the way of others, even if I read my own code still.

I desperately hope that eventually the industry will settle into some sort of a happy compromise, where human programmers can still have fun and express skill.

> there are no obvious errors,

I think ai's special power is being convincing. Whatever it produces comes across as very persuasive and looks really good. The problems are mostly only noticeable if you dig in a bit and read between the lines or check assumptions etc. Then you might find out that the entire approach or paradigm being used is irrelevant and counterproductive... oops

loading story #50548933
loading story #50552936
I’ve been doing similarly and it’s a lot of fun. If it’s a completely new architectural piece I need to write , I start by hand, explore the code a bit, write some of it and when I know it will work well just let the ai finish the job, write tests, update docs etc. It’s the ultimate programming experience: do only what you enjoy doing, outsource the boring parts to the AI! All while keeping my hands sharp and my awareness of the code base.