Skip to content
Lenny's PodcastLenny's Podcast

Chip Huyen: Why RAG wins come from data prep, not vector DBs

Preparing data and talking to users beats agonizing over which vector database; Huyen says post-training, not new models, drives real AI product wins.

Chip HuyenguestLenny Rachitskyhost
Oct 23, 20251h 22mWatch on YouTube ↗

CHAPTERS

  1. 0:00 – 4:28

    Introduction to Chip Huyen

  2. 4:28 – 7:05

    Chip’s viral LinkedIn post

  3. 7:05 – 8:50

    Understanding AI training: pre-training vs. post-training

  4. 8:50 – 13:55

    Language modeling explained

  5. 13:55 – 15:20

    The importance of post-training

  6. 15:20 – 22:23

    Reinforcement learning and human feedback

  7. 22:23 – 31:55

    The importance of evals in AI development

  8. 31:55 – 38:50

    Retrieval augmented generation (RAG) explained

  9. 38:50 – 43:19

    Challenges in AI tool adoption

  10. 43:19 – 45:20

    Challenges in measuring productivity

  11. 45:20 – 49:10

    The three-bucket test

  12. 49:10 – 55:31

    The future of engineering roles

  13. 55:31 – 57:12

    ML Engineers vs. AI engineers

  14. 57:12 – 1:05:48

    Looking forward: the impact of AI

  15. 1:05:48 – 1:08:23

    Model capabilities vs. perceived performance

  16. 1:08:23 – 1:22:35

    Lightning round and final thoughts

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome