AI 工程
AI Engineering
Chip Huyen · 初版 2024 年
6人推荐
9位读者提及
9次提及
AI 领域的近期突破不仅增加了对 AI 产品的需求，还降低了想要构建 AI 产品的人的准入门槛。model-as-a-service 模式已将 AI 从一门晦涩难懂的学科转变为任何人都可以使用的强大开发工具。如今，每个人，哪怕只有极少或根本没有 AI 经验，也可以利用 AI 模型来构建应用程序。在本书中，作者 Chip Huyen 探讨了 AI engineering：即利用现成的 foundation models 构建应用程序的过程。全书首先概述了 AI engineering……
Hacker News 上怎么说
正在加载完整评论……
……它们已经可用了（库/模型/等等），如何用它们来构建你的应用；1) 阮春（Chip Huyen）的《设计机器学习系统：生产就绪应用的迭代流程》（Designing Machine Learning Systems）。2) 阮春的《AI 工程：使用基础模型构建应用》（AI Engineering，这是一本非常新的书）。3) 戴维·福斯特（David Foster）的《生成式深度学习》（Generative Deep Learning）。4) 构建……
…that they are available (library/models/whatever), how to build your apps using them; 1) Designing Machine Learning Systems: An Iterative Process for Production-Ready Applications by Chip Huyen. 2) AI Engineering: Building Applications with Foundation Models by Chip Huyen (this is a very recent book). 3) Generative Deep Learning: Teaching Machines To Paint, Write, Compose, and Play by David Foster. 4) Building…
这不是一个完整的解决方案，但有两本书你应该立刻买来看：Martin Kleppmann 的《设计数据密集型应用》（Designing Data-Intensive Applications）和 Chip Huyen 的《AI 工程》（AI Engineering）
This is not a complete solution, but two books you should buy immediately: Designing Data-Intensive Applications by Martin Kleppmann AI Engineering by Chip Huyen
……论文。毕晓普（Bishop）最新的《深度学习：基础与概念 (2024)》（Deep Learning: Foundations and Concepts）[1] 是一本优秀的资源，涵盖了深度学习的“基础知识”，内容非常新。另一个好选择是 Chip Huyen 的《AI 工程 (2024)》[2]。还有一个极棒的选择是《动手学深度学习》（Dive into Deep Learning）[3]、《理解深度学习》（Understanding Deep Learning）[4]，或者干脆看 fast.ai 的任何资料，再加上 YouTube 上 Karpathy 的视频课。[1]: https://www.bishopbook.com……
…papers. The latest Bishop’s "Deep Learning: Foundations and Concepts (2024)" [1] is an excellent resource that covers the "basics" of deep learning and is quite updated. Another good option is Chip Huyen’s "AI Engineering (2024)" [2]. Another excellent choice will be "Dive into Deep Learning" [3], Understanding Deep Learning [4], or just read anything from fast.ai and watch Karpathy's lectures on YouTube. [1]: https://www.bishopbook.com…
……但我看的够多了，完全有信心推荐它们：- John Berryman 和 Albert Ziegler 写的《LLM 提示工程》（Prompt Engineering for LLMs）：https://www.amazon.com/Prompt-Engineering-LLMs-Model-Based-A... - Chip Huyen 的《AI 工程》（AI Engineering），我之所以推荐它是基于关于“agent”的这段精彩节选：https://huyenchip.com/2025/01/07/agents.html
…but I've seen enough of them that I'm confident suggesting them: - Prompt Engineering for LLMs by John Berryman and Albert Ziegler: https://www.amazon.com/Prompt-Engineering-LLMs-Model-Based-A... - AI Engineering by Chip Huyen, which I recommend based on the strength of this extract about "agents": https://huyenchip.com/2025/01/07/agents.html
我最近深入研读了 Chip Huyen 的《AI 工程》，其中有一个论点对当下基于 LLM 构建应用的团队来说尤为关键。那就是检索增强生成（RAG）和微调（finetuning）之间清晰且讲求原则的界限。很多工程……
I recently did a deep dive into Chip Huyen's "AI Engineering" and one argument stood out as particularly crucial for teams building with LLMs today. It's the clear, principled distinction between Retrieval-Augmented Generation (RAG) and finetuning. Many engineering…
没错；我会建议去读读 Chip Huyen 的《AI 工程》，对这个领域建立一个基础认知，再做两个相关的 side project 熟悉一下，能把用 LLM 开发的门道讲清楚，这就足够了……
Absolutely; I'd check out AI Engineering by Chip Huyen to get a fundamental understanding of the space and do a couple of side projects in the area to get familiar and be able to speak to the nuances of working with LLMs, and that will be enough…