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

61–70 of 123 posts

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

#61

Post by peri-cl »

nolok wrote: post #58
peri-cl wrote: post #52

Earlier quoted context omitted.

You find Q3 to be usable quality for your purposes? (I assume Q3 if you're squeezing it into 16 GiB)

Yes, the generic system I built has unsloth/qwen3.8-27b with a 48000 context size running on each employee system with lmstudio, with a simple runner to watch folders and pass it to the llm alongside all context (our company design rules, our legal documents, our contractual rules, our applicable local law and reglementation, ...), return is then mailed to them or added to their personal dashboard event list, dependi…

This is highly helpful to me, thank you!

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

#62

Post by chrisjj »

01100011 wrote: post #17

Lately google has been sporadically refusing to give me lyrics. Is there some new worry about copyright infringement related to displaying lyrics?

Yes. Anthropic is being sued for copying lyrics without permission en masse. https://www.theguardian.com/business/2026/aug/31/aanthropic-...

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

#63

Post by zeven7 »

peri-cl wrote: post #18
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…

Looks like Claude quietly downgraded your model (well, it's not really that quiet). That result's at a quality level similar to what local A3b Qwen drew for me, with a "make it SVG" addendum, https://i.ibb.co/ycgGD4b1/soonic.webp ( Qwen3.6-27B-A3b, a very small model )

Claude doesn’t have text to image generation, unlike Gemini and OpenAI, so like Qwen it falls back to creating an SVG through text generation

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

#64

Post by mpyne »

0x1d7 wrote: post #40
simonw wrote: post #31

Earlier quoted context omitted.

"if anything Claude was introducing me to new artists and new music"

Next time the RIAA goes after someone for downloading an MP3, tell the defendant to use that line.

RIAA doesn't like it, but my introduction to a video game series I've since spent hundreds of dollars on over the years, came from running across one of its soundtrack pieces on Youtube.

There's a reason companies talk about "customer acquistion cost", as you generally need to pay to market your products to potential customers of them.

So free marketing can be a real cost reduction. It may not be enough to be a benefit compared to the cost of piracy, but it's hardly a made-up defense.

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

#65

Post by GPerson »

simonw wrote: post #35
Maxion wrote: post #30

Earlier quoted context omitted.

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

Do you want AGI? I don't. I want the tools we've got now, but progressively more effective and more useful.

You don’t act like you don’t want AGI. You have a very strong track record of speaking out of both sides of your mouth in different settings.

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

#66

Post by ValentineC »

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.

Isn't it more that the "Chinese models" are open weight?

Also, the system prompt in the article is supposedly for the web version, so I think the $$$ API version or providers that still allow third-party harnesses like OpenAI should have fewer limitations.

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

#67

Post by gxqoz »

How new is this? About a month ago I tried to get Claude (forget which model but probably Opus 5) to transcribe a low-res hand-written lyric sheet from a relatively obscure punk band and it refused.

Of course, since then I had the idea of having it build for me an automatic solution for charting out songs in Clone Hero, a Rock Band clone. It had no problem ripping the audio from YouTube, using Whisper to generate and match the timing of the vocals, etc. Responsible AI at work.

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

#68

Post by qarl2 »

simonw wrote: post #37
qarl2 wrote: post #34

Re: end_conversation All tools have short descriptions of how/when to use them. They're not part of the system prompt because different users have different tools loaded.

I really wish Anthropic would publish those tool descriptions. I learned a ton of useful things about ChatGPT Work by having it dump out its tool descriptions the other day: https://codex-tool-reference.simonw.chatgpt.site/

The web Claude wouldn't tell me, but Claude Code had no reservations:

   EndConversation (deferred tool): use only for sustained user abuse directed
   at the assistant, or when the user explicitly asks to see it demonstrated.
   Load the full guidance via ToolSearch("select:EndConversation") before using
   it.
There's a much more detailed set of instructions that are provided when the agent goes to invoke it:

https://snowday.s3.amazonaws.com/store/6097125d0a169554063dd...

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

#70

Post by simonw »

GPerson wrote: post #65
simonw wrote: post #35

Earlier quoted context omitted.

Do you want AGI? I don't. I want the tools we've got now, but progressively more effective and more useful.

You don’t act like you don’t want AGI. You have a very strong track record of speaking out of both sides of your mouth in different settings.

I've been pretty consistent about my disinterest in AGI: https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...

"You have a very strong track record of speaking out of both sides of your mouth in different settings."

If I have a consistent record of that it should be very easy for you to come up with the some examples.

Post reply on HN