Ask HN: How does everyone talk about their work when they've used AI? | Hacker News Reader

Ask HN: How does everyone talk about their work when they've used AI?

6 pointsdeku209910 comments

Hi! I was working on a couple of personal projects, and I've been using Claude Code for a while. Recently, I've been wanting to talk about my work publicly, but I started to think about how I would exactly talk about it, given the fact that I used AI to build some of the projects. There were entire features that I had Claude Code write for me, and although I did write a spec and design it, it still kinda feels a little wrong, like pseudo-plagiarism.

Wanted to know how everyone is talking about their work while using AI. Do y'all mention the fact that you're using AI, or do you keep mum about it?

View on HN

Just be up front about it; these tools are a simple reality at this point. Own the usage, own the output, take responsibility for the totality of what you’ve birthed into the world. If it’s some one-shotted trinket, don’t pretend it isn’t. If it’s some 5000-commit battle-tested magnum opus that you happened to spend a year driving an LLM to create, own that too. IMO it doesn’t matter if you dug the hole for your Olympic-sized swimming pool by hand with a shovel or using heavy machinery, I’m more interested in the quality of the final product.

Personally, I don't broadcast it, but if anyone asks I'm completely honest. I've got one project written in Swift that's up to nearly 50k lines of code and it's taken months to do from spec'ing it to debugging it to hand cranking all the CI/CD release process. A graphical MacOS native app isn't easy for me to craft prompts for and LLMs can't SEE what I'm trying to describe to it. I'm also learning Swift as I go. So quite proud of it AI or not.

I usually talk more about the decisions/tradeoffs than who typed the code.

Using AI changed implementation speed for me way more than it changed product direction.

Python, strip ANSI escape codes regexp. Copy-paste regexp. Bam, done. I'm comfortable with delegating such menial, low-value tasks. I can focus on the important tasks. I'm a much stronger coder than the bot but also lazy.

If you understand how your project works and it solves a real problem, whether it was hand-crafted or AI-assisted doesn't really matter.

AI does not remove authorship if you are still making the architectural decisions.

I increasingly describe AI as part of the workflow, not the author of the work.

i dont mention AI b/c people already know i used it without saying. if anything its the opposite - i have to highlight that smth is hand made when i want to look crazy

well, if you're in a context of what AI did - everything is fine IMO

I have no shame mentioning my use of AI. It's a tool to get things done. Would you feel the same 10 years ago if you leveraged your IDE's auto-complete, generate getter/setter, create/refactor method, etc. functionality. Probably not. As long as you conceptually understand the domain, architecture and feature set, you're good.

If you are generating a bunch of slop and don't bother to review, guide or understand what's going on... then there might be a problem. But honestly, that's speaking for today. Down the line, who knows?

Software development as a whole might become more of a product role. Can you gather feedback and requirements and put them into clear understandable terms for AI to implement. And even then, that'll be abstracted too. I'm already leveraging AI to propose new features and to document current features.

It's an exciting time. Don't feel bad about leveraging the right tool for the job unless you are misusing it without bothering to gain experience and learn.

Reply on news.ycombinator.com