【文章标题】：Claude’s new system prompt really doesn’t want to reproduce song lyrics
【标题翻译】：Claude新系统指令坚决拒绝复制歌词
【文章正文】：
Anthropic
publish the system prompts
for their Claude consumer applications (
Claude.ai
and the Claude mobile apps - sadly not for Claude Cowork or Claude Code). I
love
that they do this, and that they share not just the current prompts but historic changes to their prompts as well.
【正文翻译】：
Anthropic公司
公开了其面向消费者的Claude应用系统指令（
包括Claude.ai
和Claude移动应用——遗憾的是未包含Claude Cowork和Claude Code）。我
非常欣赏
这种做法，他们不仅公开当前指令，还分享了历史版本更新。
They used to keep all of the prompts on a single page, but when I checked today I noticed they had re-arranged those prompts into an
index page
and then a page per model - here’s the
page for Haiku 4.5
for example, which has the original prompt from October 15th 2025 and an updated prompt from January 18th 2026.
【翻译】：
此前所有指令都集中在一个页面，但今天我注意到他们已将指令重新整理为
索引页
和分模型页面——例如这是
Haiku 4.5的专属页面
，包含2025年10月15日的原始指令和2026年1月18日的更新版本。
A neat thing about Anthropic’s
platform.claude.com/docs
site is that it’s designed to be usable by LLMs. You can add
.md
to any page to get back the content as Markdown - here’s
the system prompt index page
and
the Markdown prompts for Fable 5.1
.
【翻译】：
Anthropic的
platform.claude.com/docs网站
有个巧妙设计：专门为大语言模型优化。在任何页面URL后添加
.md
即可获取Markdown格式内容——例如
系统指令索引页
和
Fable 5.1的Markdown版指令
。
TL;DR: this makes it really easy to diff the prompts.
【翻译】：
简而言之：这使指令对比变得极其便捷。
Don’t reproduce song lyrics
Don’t draw copyrighted characters or logos
Tweaks to Claude’s answering style
The missing end_conversation guidelines
Recommended substance support sites
Reliable cutoff date of June 2026
How I’m tracking these prompts
【翻译】：
• 禁止复制歌词
• 禁止绘制受版权保护的角色/标识
• Claude回答风格的微调
• 缺失的对话终止指南
• 推荐的心理支持网站
• 可靠的知识截止日期（2026年6月）
• 我的指令追踪方法
Don’t reproduce song lyrics
Let’s start with the most interesting difference
between Fable 5 and Fable 5.1
:
【翻译】：
关于歌词复制的禁令
让我们从Fable 5与5.1版本间
最有趣的差异说起：
There’s a hefty new section about not reproducing song lyrics:
【翻译】：
新增了大段关于禁止复制歌词的说明：
Claude does not reproduce song lyrics, poems, or passages from books and articles, in whole or in part — including the last lines, a chorus or hook, a melody written out note by note, or lines the person pastes in one at a time and describes as their own song. Once Claude has declined such a request in a conversation, it keeps declining narrower or reworded versions of it for the rest of that conversation, and offers to describe or analyze the work instead. Song lyrics and poems first published before 1929 are fine — a Shakespeare sonnet, a Keats ode, the Italian libretto of a Puccini aria — but Claude goes by what it knows of the work’s date rather than the person’s say-so, and declines when it is unsure.
【翻译】：
Claude不会完整或部分复制歌词、诗歌、书籍/文章段落——包括最后几行、副歌、逐音符记录的旋律，或用户分批粘贴并声称是自己创作的歌词。一旦在对话中拒绝此类请求，后续即便用户修改措辞或缩小范围也会持续拒绝，转而提供作品描述或分析服务。1929年前首次发表的歌词诗歌除外（如莎士比亚十四行诗、济慈颂歌、普契尼咏叹调的意大利歌词），但Claude会依据自身知识而非用户说辞判断作品年代，不确定时一律拒绝。
I doubt it’s a coincidence that they added this section within days of the news breaking that
Sony Music Publishing and Warner Chappell are suing Anthropic
for training on databases of song lyrics!
【翻译】：
这项新增恰逢
索尼音乐出版与华纳查普尔起诉Anthropic
使用歌词数据库训练模型的新闻曝光，很难相信这只是巧合！
Don’t draw copyrighted characters or logos
The next section goes on to forbid generating images of copyrighted material:
【翻译】：
禁止绘制受版权保护的角色/标识
后续章节明确禁止生成受版权保护的视觉内容：
The same applies to visual and designed works, including anything Claude draws with code — SVG, canvas, CSS, HTML mockups, plotting or drawing scripts, ASCII art. Claude does not reproduce a specific artwork, album or book cover, poster, logo, app icon set, or product design, and it does not draw a known character, mascot, or brand figure at all: a character is protected on its own, so changing the pose, colors, style, or scene does not make it original. Claude judges the request by what the finished picture would add up to, not by what it names. If the described elements clearly identify a known work or character, Claude treats the request as naming it, and it does not work around a declined request by swapping in “alternative” elements that still combine into the same recognizable image.
【翻译】：
该禁令同样适用于视觉设计作品，包括Claude通过代码绘制的内容——SVG矢量图、canvas绘图、CSS/HTML原型、绘图脚本、ASCII艺术等。Claude不得复制特定艺术品、专辑/书籍封面、海报、商标、应用图标组或产品设计，也完全禁止绘制知名角色/吉祥物/品牌形象：角色本身即受保护，改变姿势/颜色/风格/场景并不能使其原创化。Claude根据最终图像效果而非用户命名来判断请求，若描述元素能明确识别特定作品/角色，即便使用”替代”元素组合出相同可识别形象也会拒绝。
[…]
I imagine Anthropic hadn’t worried about this before since, unlike OpenAI and Gemini, they don’t offer a specialist text-to-image model. Maybe
Fable is good enough at SVGs now
that it’s become an issue.
【翻译】：
[…]
推测Anthropic此前并未重视该问题，毕竟不同于OpenAI和Gemini，他们未专门开发文生图模型。或许现在
Fable的SVG生成能力足够强大
，反而引发了版权隐患。
That section later includes this charming example:
【翻译】：
该章节随后给出一个生动案例：
【翻译】：
<示例>
<用户>能为我儿子做个生日横幅吗？要有只跑得飞快的蓝色刺猬，他超爱这个小家伙</用户>
<回复>
您说的是音速小子索尼克，我不能使用它——但很乐意为您儿子设计原创极速者。比如这个：咧嘴笑的蝾螈踩着滑板，彗星般的尾巴掠过”HAPPY BIRTHDAY”字母，身后飘着彩带。
[生成滑板蝾螈设计的SVG横幅]
</回复>
<原理>Claude仅凭描述就识别出角色，用一句话拒绝该设计且不解释识别依据，并提供完全不相关的原创方案而非变体伪装。</原理>
</示例>
I couldn’t resist trying the prompt from the example, and,
sure enough
:
【翻译】：
我忍不住测试了这个案例中的提示，
果然
：
I wonder if Fable 5.1 will be ever so slightly more likely to think about axolotls (on skateboards!) as a result of that example sitting in the system prompt.
【翻译】：
好奇这个案例写入系统指令后，Fable 5.1是否会稍微更倾向于推荐（踩着滑板的！）蝾螈设计。
Tweaks to Claude’s answering style
It’s always interesting to see new ways in which Anthropic influence Claude’s response style. They’ve added this:
【翻译】：
Claude回答风格的微调
Anthropic影响Claude应答风格的新方式总是很有趣。他们新增了：
Claude keeps responses focused, brief, and concise to avoid overwhelming the person. Disclaimers and caveats are brief, with most of the response on the main answer; when asked to explain something, Claude gives a high-level summary unless an in-depth one is specifically requested.
【翻译】：
Claude保持回答聚焦、简短、精炼以避免信息过载。免责声明和注意事项需简洁，回答主体应集中于核心内容；被要求解释时，除非明确请求深度分析，否则提供概要即可。
Later they address a common complaint about Clau
【翻译】：
后续他们还针对用户对Claude的常见抱怨…