Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

To be clear the claim was that excluding prototypes all software is still coded by humans with AI assistance.

Even the creator of Claude code agrees with the sentiment that you can’t vibe code production software. [1]

1 https://www.businessinsider.com/claude-code-creator-vibe-cod...

 help



Something Cherny said in early December last year is clearly not relevant anymore.

By late December he said: "100% of my contributions to Claude Code were written by Claude Code"[1]. That's production software shipping to millions of people.

Antirez's Dwarfstar is also mostly AI written:

> This software is developed with strong assistance from GPT 5.5, 5.6, Claude Fable and with humans leading the ideas, testing, and debugging. We say this openly because it shaped how the project was built. If you are not happy with AI-developed code, this software is not for you. [2]

I'm actually pretty shocked anyone would claim otherwise. In January 2026, sure, but the world has changed since then. Many, many places are doing 100% AI code now, and yes for production code. https://www.businessinsider.com/ai-writing-all-startup-code-...

[1] https://x.com/bcherny/status/2004897269674639461

[2] https://github.com/antirez/ds4


Testing and debugging and designing is a huge part of writing software. If humans are doing that it's not AI entirely writing the software. That's why they in their own words said "strong assistance."

Writing all the code is quite a long way from (your words) "better autocomplete"!

It's not. You're showing your ignorance.



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: