玩法 · 2025 年 9 月首次出现 · 1 档 2 期

AI Eval人才

怎么聊起来的

  1. 2025 年 9 月新

    AI评估成产品人最热新技能，Mercor等公司靠Eval缔造最快增长，专家写Eval是核心竞争力。2 期

哪些节目在讲

2 期 · 12 个片段

  • Why AI evals are the hottest new skill for product builders | Hamel Husain & Shreya Shankar (creators of the #1 eval course)

    Lenny's Podcast · 2025-09-25 · 107 分钟

    原站 ↗
    1. 04:57What are evals?
    2. 25:16The concept of a “benevolent dictator” in the eval process
    3. 46:06Building an LLM-as-judge to evaluate specific failure modes
    4. 48:31The difference between code-based evals and LLM-as-judge
    5. 01:00:51Why evals are the new PRDs for AI products
    6. 01:05:09How many evals you actually need
    7. 01:07:41What comes after evals
    8. 01:09:57The great evals debate
    9. 01:24:13Common misconceptions around evals
    10. 1:22:28Tips and tricks for implementing evals effectively
    11. 1:33:38Overview of their comprehensive evals course

  • Why experts writing AI evals is creating the fastest-growing companies in history | Brendan Foody (CEO of Mercor)

    Lenny's Podcast · 2025-09-18 · 67 分钟

    原站 ↗
    1. 05:38The “era of evals”