The MAD Podcast with Matt Turck What You MUST Know About AI Engineering in 2025 | Chip Huyen, Author of “AI Engineering”
51 snips
Jan 16, 2025 Chip Huyen, an esteemed AI engineer and author, shares his insights on AI engineering. He distinguishes AI engineering from traditional machine learning, explaining how foundational models democratize app development. Huyen dives into the crucial role of prompt engineering and the complexities of AI model evaluation. With a closer look at the generative AI stack, he dispels myths around Retrieval-Augmented Generation (RAG) and discusses the evolving nature of AI agents. This conversation is a treasure trove for anyone interested in the future of AI technology.
AI Snips
Chapters
Books
Transcript
Episode notes
AI Engineering vs. Traditional ML
- AI engineering differs from traditional ML because it leverages readily available foundation models.
- This accessibility empowers anyone to build AI applications, leading to an explosion of new ideas and products.
AI Evaluation Challenges
- Evaluating AI models is harder than traditional ML due to nuanced outputs like summaries.
- Silent failures and the complexity of judging advanced AI outputs pose significant challenges.
Product-First Approach
- Building AI applications now often follows a product-first approach, unlike traditional ML's data-first.
- This shift prioritizes product ideas and demos, with data and model investment following later if successful.
