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

Claude's new system prompt doesn't want to reproduce song lyrics

simonwillison.net

Post reply on HN
Print view View original

21–30 of 120 posts

Re: Claude's new system prompt doesn't want to reproduce song lyrics

#21

Post by stwrt »

nolok wrote: post #8
IChooseY0u wrote: post #2

This is something that Chinese models like Kimi/GLM will never care about. These kind of limitations along with the cyber-program nonsense is exactly why people will avoid OpenAI/Anthropic in the future.

Qwen 3.8 27B being so good, so easy to run on premise on cheap hardware and having so little limitations compared to what the US decides can or cannot be done is really eye opening.

The main tradeoff I’ve found with running models like Qwen 3.8 locally is speed. On my hardware, they’re significantly slower than models served through OpenRouter, ChatGPT, or Claude.

That’s been fine for smaller tasks like analyzing a document, but for more involved work like refactoring code the latency makes it harder to iterate.

Re: Claude's new system prompt doesn't want to reproduce song lyrics

#23

Post by pnw »

SyneRyder wrote: post #15

I'm sad about the lyrics restrictions. I used to have interesting conversations with Claude about music, and songwriting and lyrics. I don't see how my use was harming artists, if anything Claude was introducing me to new artists and new music. I've bought music after recommendations by Claude. Claude Sonnet 3.6 once recommended I listen to Johann Johannsson's album "IBM 1401 - A User's Manual". No lyrics in this one…

Great album and backstory. You can't really go wrong with anything he composed. Rest in peace Johann.

Re: Claude's new system prompt doesn't want to reproduce song lyrics

#24

Post by nolok »

stwrt wrote: post #21
nolok wrote: post #8

Earlier quoted context omitted.

Qwen 3.8 27B being so good, so easy to run on premise on cheap hardware and having so little limitations compared to what the US decides can or cannot be done is really eye opening.

The main tradeoff I’ve found with running models like Qwen 3.8 locally is speed. On my hardware, they’re significantly slower than models served through OpenRouter, ChatGPT, or Claude. That’s been fine for smaller tasks like analyzing a document, but for more involved work like refactoring code the latency makes it harder to iterate.

Yeah for live it's a bit on the slower side though still usable on the 4070 ti and 5080 our usual office desk has here, but I found it awesome running on background tasks rather than on demand, things like analyze this and that with this and that ruleset and applicable law warn me with source and justification for any error or missing part etc, qualify each returns with a ranking (certain with source, probable with reason, suggestion),... With its thinking mode enabled and it's great context size abilities it's really powerful, and each employee basically has their own assistant working in the background checking their files on its own as the day progresses

(the main reason is not just cost, it's data not going out and even mess leaving the EU, this essentially frees us of a lot of hurdles)

Re: Claude's new system prompt doesn't want to reproduce song lyrics

#25

Post by Redster »

Bluestein wrote: post #14
piker wrote: post #11

Earlier quoted context omitted.

ChatGPT was happy to infringe: https://chatgpt.com/s/m_6a9c30da3bcc8191bb5203f1cb22f16a As was Gemini: https://share.gemini.google/Q3EIX5wk64zC Grok, too: https://grok.com/share/bGVnYWN5LWNvcHk_aaf1d61a-c995-42ca-90... claude.ai free tier refused: "I'd love to make this, but I can't recreate Sonic the Hedgehog specifically since he's a copyrighted character — I don't want to reproduce someone else's IP. What I can do…

Claude's is a ... deformed, vectorized, geometric ... blob? :/

I love that little guy! lol

Re: Claude's new system prompt doesn't want to reproduce song lyrics

#28

Post by janpeuker »

I'm not sure if it's just the new prompt - this has happened to a comical degree for me since a long time. For example it even refuses to translate even just single verses of old songs, I asked for a translation of Tu vuò fà l'americano once. Niente.

Re: Claude's new system prompt doesn't want to reproduce song lyrics

#29

Post by nolok »

tiahura wrote: post #6
IChooseY0u wrote: post #2

This is something that Chinese models like Kimi/GLM will never care about. These kind of limitations along with the cyber-program nonsense is exactly why people will avoid OpenAI/Anthropic in the future.

In the future we'll all use multiple models.

We would be doing it now if it wasn't cutting into frontier companies' revenue.

Eg if you use Claude, you probably want fable architecting, a couple of opus under it managing sub project and sonnet doing the actual function code, because fable coding a "run a query and filter the result" is a massive waste of abilities. But their own sub agent downgrade is limited to one level so if you use fable it will never direct sonnet coders.

Re: Claude's new system prompt doesn't want to reproduce song lyrics

#30

Post by Maxion »

hasteg wrote: post #16
layer8 wrote: post #7

It’s curious that while there is talk of certain SOTA models being on the brink of AGI, Anthropic doesn’t word this part of the system prompt in terms of copyright and plagiarism, such that Claude would be able to judge on its own which reproductions are appropriate or not. As long as we’re seeing things like that, it’s saying a lot about the AI companies’ trust in the capabilities and reliability of their models and…

That’s a good point… you would think AGI would be better at being a copyright lawyer than any human would be and as such would be able to distinguish whether something is “copyright infringement” or not… so the system prompt should just include “make judgement calls on reproducing copyrighted material under the full scope of the legal framework in place” or something.

The whole architecture of current LLMs just is not conductive to AGI, it's just marketing hype. In my opinion current LLMs aren't even AI, they're just fancy machine learning algorithms
Post reply on HN