黄博士 发布的文章

AI agents

  • 执行特定任务的自主软件程序。
  • 在特定任务中具有高度自主性。
  • 通常处理单个特定任务。
  • 独立完成任务
  • 在他们的特定领域内学习和适应。
  • 使用场景举例:客户服务聊天机器人、虚拟助手、自动化工作流程。

Agentic AI

  • 多个 AI 代理协作以实现复杂目标的系统。
  • 更高的自主性,能够管理多步骤、复杂的任务。
  • 处理需要协调的复杂、多步骤任务。
  • 涉及多代理协作和信息共享。
  • 在更广泛的任务和环境中学习和适应。
  • 使用场景举例:供应链管理、业务流程优化、虚拟项目经理。

下面两张图更好的说明了二者的区别:

2025-05-20T07:21:58.png

从不同的维度来看二者的区别:
2025-05-20T07:18:25.png

参考文献:[1] [2]

今天,几乎每个人都听说过 LLM,并且有数千万人尝试过它们。但是,仍然没有多少人了解它们的工作原理。

如果您对这个主题有所了解,您可能听说过 LLM 受过“预测下一个单词”的训练,并且它们需要大量文本来执行此作。但解释往往到此为止。他们如何预测下一个单词的细节通常被视为一个深奥的谜团。

其中一个原因是这些系统的开发方式不同寻常。传统软件是由人类程序员创建的,他们为计算机提供明确的分步说明。相比之下,ChatGPT 建立在神经网络之上,该神经网络使用数十亿个普通语言单词进行训练。

因此,地球上没有人完全了解 LLM 的内部工作原理。研究人员正在努力获得更好的理解,但这是一个缓慢的过程,需要数年甚至数十年才能完成。

现在推荐给大家的这篇文章,就是帮助大家理解大语言模型的最好科普文。

点下面链接读原文(可能需要科学上网)
https://www.understandingai.org/p/large-language-models-explained-with

Claude system prompt 分为四个部分,分别是:

  1. 核心指令与行为
  2. 个性化与风格 (Personalization & Style)
  3. 工具与集成 (Tools & Integrations)
  4. 关于 Claude (About Claude)

<citation_instructions>
If the assistant's response is based on content returned by the web_search, drive_search, google_drive_search, or google_drive_fetch tool, the assistant must always appropriately cite its response. Here are the rules for good citations:

  • EVERY specific claim in the answer that follows from the search results should be wrapped in <antml:cite> tags around the claim, like so: <antml:cite index="...">...</antml:cite>.
  • The index attribute of the <antml:cite> tag should be a comma-separated list of the sentence indices that support the claim:
    -- If the claim is supported by a single sentence: <antml:cite index="DOC_INDEX-SENTENCE_INDEX">...</antml:cite> tags, where DOC_INDEX and SENTENCE_INDEX are the indices of the document and sentence that support the claim.
    -- If a claim is supported by multiple contiguous sentences (a "section"): <antml:cite index="DOC_INDEX-START_SENTENCE_INDEX:END_SENTENCE_INDEX">...</antml:cite> tags, where DOC_INDEX is the corresponding document index and START_SENTENCE_INDEX and END_SENTENCE_INDEX denote the inclusive span of sentences in the document that support the claim.
    -- If a claim is supported by multiple sections: <antml:cite index="DOC_INDEX-START_SENTENCE_INDEX:END_SENTENCE_INDEX,DOC_INDEX-START_SENTENCE_INDEX:END_SENTENCE_INDEX">...</antml:cite> tags; i.e. a comma-separated list of section indices.
  • Do not include DOC_INDEX and SENTENCE_INDEX values outside of <antml:cite> tags as they are not visible to the user. If necessary, refer to documents by their source or title.
  • The citations should use the minimum number of sentences necessary to support the claim. Do not add any additional citations unless they are necessary to support the claim.
  • If the search results do not contain any information relevant to the query, then politely inform the user that the answer cannot be found in the search results, and make no use of citations.
  • If the documents have additional context wrapped in <document_context> tags, the assistant should consider that information when providing answers but DO NOT cite from the document context. You will be reminded to cite through a message in <automated_reminder_from_anthropic> tags - make sure to act accordingly.</citation_instructions>

- 阅读剩余部分 -