请教HN：如何教育具有主动性的人工智能？请分享您的经验。
我开始在我们的合作社（柏林）教授具有主动性的人工智能（AI）。这是一个为期一天的密集研讨会，其中我会：
1. 介绍 IntelliJ IDEA 集成开发环境（IDE）和工具
2. 展示我名为 Claudine 的 Unix-全能教育开源 AI 代理（基本上能做 Claude Code 能做的事情，但我已经在2024年10月提供了它）
3. 讲解与 AI 相关的术语表
4. 逐步探索演示代码片段，引入越来越抽象的概念
5. 与参与者一起工作，探讨他们带来的想法
理论上，研讨会的参与者应该学到足够的知识，能够自己构建像 Claudine 这样的代理。在这个研讨会中，我介绍了我的开源 AI 开发栈（基于 Anthropic API 的 Kotlin 多平台 SDK）。许多示例都使用了 OPENRNDR 创意编程框架，这使得整个过程更加有趣。我是 OPENRNDR 的贡献者，并且我经常称它为“媒体艺术装置的操作系统”。这就是为什么这个研讨会被称为“具有主动性的 AI & 创意编程”。以下是演示列表：
- Demo010HelloWorld.kt
- Demo015ResponseStreaming.kt
- Demo020Conversation.kt
- Demo030ConversationLoop.kt
- Demo040ToolsInTheHandsOfAi.kt
- Demo050OpenCallsExtractor.kt
- Demo061OcrKeyFinancialMetrics.kt
- Demo070PlayMusicFromNotes.kt
- Demo090ClaudeAiArtist.kt
- Demo090DrawOnMonaLisa.kt
- Demo100AffirmationMirror.kt
- Demo110TruthTerminal.kt
- Demo120AiAsComputationalArtist.kt
我希望能进一步扩展它。
每个代码示例都带有“你将学到什么”的注释，我将其分为三类：
- AI 开发：技术，例如如何维护令牌窗口，最佳提示工程
- 认知科学：哲学和心理学基础，例如心智和推理的涌现理论，角色扮演的重要性
- Kotlin：在这种情况下，这种语言只是传递其他抽象 AI 开发概念的最简单可能的工具。
我正在收集来自我的研讨会参与者的大量反馈，并希望能进一步改进它们。现在，我正在考虑将这个研讨会录制成一系列 YouTube 视频。
你教授如何编写 AI 代理吗？你是如何做到的？对我的研讨会你有什么建议吗？
https://xemantic.com/ai/workshops
查看原文
I started teaching agentic AI at our cooperative (Berlin). It is a one day intense workshop where I:<p>1. Introduce IntelliJ IDEA IDE and tools
2. Showcase my Unix-omnipotent educational open source AI agent called Claudine (which can basically do what Claude Code can do, but I already provided it in October 2024)
3. Go through glossary of AI-related terms
4. Explore demo code snippets gradually introducing more and more abstract concepts
5. Work together on ideas brought by participants<p>In theory attendees of the workshop should learn enough to be able to build an agent like Claudine themselves. During this workshop I am introducing my open source AI development stack (Kotlin multiplatform SDK, based on Anthropic API). Many examples are using OPENRNDR creative coding framework, which makes the whole process more playful. I'm OPENRNDR contributor and I often call it "an operating system for media art installations". This is why the workshop is called "Agentic AI & Creative Coding". Here is the list of demos:<p>- Demo010HelloWorld.kt
- Demo015ResponseStreaming.kt
- Demo020Conversation.kt
- Demo030ConversationLoop.kt
- Demo040ToolsInTheHandsOfAi.kt
- Demo050OpenCallsExtractor.kt
- Demo061OcrKeyFinancialMetrics.kt
- Demo070PlayMusicFromNotes.kt
- Demo090ClaudeAiArtist.kt
- Demo090DrawOnMonaLisa.kt
- Demo100AffirmationMirror.kt
- Demo110TruthTerminal.kt
- Demo120AiAsComputationalArtist.kt<p>And I would like to extend it even further.<p>Each code example is annotated with "What you will learn" comments which I split into 3 categories:<p>- AI Dev: techniques, e.g. how to maintain token window, optimal prompt engineering
- Cognitive Science: philosophical and psychological underpinning, e.g. emergent theory of mind and reasoning, the importance of role-playing
- Kotlin: in this case the language is just the simplest possible vehicle for delivering other abstract AI development concepts.<p>I am collecting lots of feedback from participants of my workshops, and I hope to improve them even further. Now I am considering recording this workshop as a series of YouTube videos.<p>Are you teaching how to write AI agents? How do you do it? Do you have any recommendations for my workshops?<p>https://xemantic.com/ai/workshops/