跳到主要内容

最新播客 知识。

Podwise 处理的新节目,随时可搜索、浏览,并在完整应用中继续。

刚刚摘要

在按下播放前,先读读每集讲了什么。

Stanford Online

Stanford CS329A Self-Improving AI Agents | Part 9 | Future Research Areas

AI 摘要 Self-improving agents utilize test-time and train-time scaling, driven by verifiers and reinforcement learning to enhance reasoning in domains like math and coding. Achieving generalization requires diverse reasoning chains, often generated by multi-agent systems or iterative…

  • LLMs (Large Language Models)
  • Test-time Scaling
  • Train-time Scaling

English摘要 · 转录

Easy German: Learn German with native speakers | Deutsch lernen mit Muttersprachlern

710: Warum lebt Manuel so ordentlich?

AI 摘要 Die persönliche Organisation und das Streben nach Ordnung stehen im Mittelpunkt, wobei die Diskussion die neurobiologischen Grundlagen von ADHS und das Konzept der Neurodiversität beleuchtet. Während feste Systeme für manche Menschen eine notwendige Stütze im Alltag darstellen,…

  • DSGVO
  • Truth Social
  • ADHS

30:59German摘要 · 转录

Stanford Online

Stanford CS329A Self-Improving AI Agents | Part 7 | Self-Improvement and Deep Research Agents

AI 摘要 Improving large language model performance relies on leveraging search within the model's output space to curate high-quality solutions. AlphaCode demonstrated that massive-scale sampling, combined with filtering and clustering, allows models to solve complex competitive…

  • AlphaCode / AlphaCode 2
  • HumanEval
  • Gemini Pro

English摘要 · 转录

The Audit Podcast

IA on AI - Fall 2026 Audit Analytics & AI Conference: Key Takeaways

AI 摘要 The fall 2026 Audit Analytics & AI Conference emphasized practical, production-ready AI applications for internal audit departments. Effective strategies include persona-based reporting, where AI agents tailor communication styles to specific stakeholder preferences, and…

  • Benford's Law
  • Persona-based reporting
  • Shadow IT

19:15English摘要 · 转录

Stanford Online

Stanford CS329A Self-Improving AI Agents | Part 6 | Train Time Scaling/Scaling RL

AI 摘要 Train time scaling enhances AI reasoning capabilities by allowing models to learn from their own outputs, effectively substituting compute for parameter count. This approach leverages verification-rich domains like mathematics and coding to create closed-loop feedback systems.…

  • Train Time Scaling
  • Test Time Scaling
  • AIME (American Invitational Mathematics Examination)

English摘要 · 转录

更多新节目

  1. How Zeneca Made $2.5M Trading AI Agents

    Milk Road Crypto

    摘要00:55:24
  2. How to Build a 100x Crypto Moon Bag w/ Zeneca

    Milk Road Crypto

    摘要00:32:40
  3. 摘要00:27:38
  4. 摘要00:27:42
  5. 摘要01:07:35
  6. 摘要46 min
  7. #2543 - MrBallen

    The Joe Rogan Experience

    摘要3 h 2 min
  8. Kyiv hit by major Russian attack

    Global News Podcast

    摘要29 min
  9. 摘要02:52:13
  10. 448. The psychology of reputation

    The Psychology of your 20s

    摘要43 min
  11. 摘要18:24
  12. So I tried Matt's skills...

    Theo - t3․gg

    摘要38 min
  13. 摘要
  14. SWE-Bench is getting replaced???

    Theo - t3․gg

    摘要33 min
  15. Sharing the road with driverless cars

    6 Minute English

    摘要7 min
  16. 摘要43 min
  17. 摘要00:30:46
  18. 摘要00:24:41
  19. 摘要00:43:36
  20. The Troubles: The Brink of Civil War (Part 2)

    The Rest Is History

    摘要1 h 22 min
  21. 摘要00:43:32
  22. 摘要00:47:09
  23. Golden Dome: Early assessment and open questions

    Brookings Institution

    摘要
  24. 摘要00:43:18
  25. Joseph Goldstein On How To Train Your Runaway Brain

    10% Happier with Dan Harris

    摘要01:08:45
Podwise

每一集新节目 都有摘要。

在 Podwise 关注你的节目,在决定收听前先读每集新节目。