Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Design System Prompt

github.com

Post reply on HN
Print view View original

31–35 of 35 posts

Re: Claude Design System Prompt

#31

Post by colinhb »

smokel wrote: post #26
dahart wrote: post #25

Earlier quoted context omitted.

What do you mean? https://opensource.org/license/mit

You cannot claim authorship of something that you were not even allowed to take in the first place. How would you then allow rights to somebody else? Seems pretty obvious to me.

In general I agree with you, especially about how things should work, and find the current trend of claiming LLM-washing code hugely problematic.

I do wonder what the analysis would be of these prompts were vibe-coded, though, since in general LLM output can’t be copyrighted without significant human authorship, and Anthropic is pretty noisy about minimal human supervision.

Re: Claude Design System Prompt

#32

Post by jdiff »

colinhb wrote: post #31
smokel wrote: post #26

Earlier quoted context omitted.

You cannot claim authorship of something that you were not even allowed to take in the first place. How would you then allow rights to somebody else? Seems pretty obvious to me.

In general I agree with you, especially about how things should work, and find the current trend of claiming LLM-washing code hugely problematic. I do wonder what the analysis would be of these prompts were vibe-coded, though, since in general LLM output can’t be copyrighted without significant human authorship, and Anthropic is pretty noisy about minimal human supervision.

The minimal human supervision for prompts seems like a pretty silly take. LLMs are still pretty bad at creating good prompts for LLMs. Give it a benchmark and some feedback and it can brute force it, but far less effectively. And I thought the point of using LLMs for development was increased efficiency.

Re: Claude Design System Prompt

#33

Post by colinhb »

jdiff wrote: post #32
colinhb wrote: post #31

Earlier quoted context omitted.

In general I agree with you, especially about how things should work, and find the current trend of claiming LLM-washing code hugely problematic. I do wonder what the analysis would be of these prompts were vibe-coded, though, since in general LLM output can’t be copyrighted without significant human authorship, and Anthropic is pretty noisy about minimal human supervision.

The minimal human supervision for prompts seems like a pretty silly take. LLMs are still pretty bad at creating good prompts for LLMs. Give it a benchmark and some feedback and it can brute force it, but far less effectively. And I thought the point of using LLMs for development was increased efficiency.

My independent judgement and experience is along your lines, but I’m trying to also take Anthropic seriously:

> “I don’t prompt Claude anymore. I have loops running that prompt Claude and figuring out what to do. My job is to write loops.”

> “Can confirm Claude Code is 100% written by Claude Code”

Both from head of Claude Code. Taken either literally or seriously they point to Anthropic shipping code with limited human authorship.

Re: Claude Design System Prompt

#35

Post by jdiff »

colinhb wrote: post #33
jdiff wrote: post #32

Earlier quoted context omitted.

The minimal human supervision for prompts seems like a pretty silly take. LLMs are still pretty bad at creating good prompts for LLMs. Give it a benchmark and some feedback and it can brute force it, but far less effectively. And I thought the point of using LLMs for development was increased efficiency.

My independent judgement and experience is along your lines, but I’m trying to also take Anthropic seriously: > “I don’t prompt Claude anymore. I have loops running that prompt Claude and figuring out what to do. My job is to write loops.” > “Can confirm Claude Code is 100% written by Claude Code” Both from head of Claude Code. Taken either literally or seriously they point to Anthropic shipping code with limited hum…

Oh I certainly believe them. And on some level I admire the dogfooding. It just seems awful foolish of them.
Post reply on HN