Skip to content

Latest podcast knowledge.

New episodes processed by Podwise, ready to search, skim and continue in the full app.

Just summarized

Read what each episode covers before you press play.

Stanford Online

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

AI summary 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

EnglishSummary · Transcript

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

710: Warum lebt Manuel so ordentlich?

AI summary 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

30:59GermanSummary · Transcript

Stanford Online

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

AI summary 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

EnglishSummary · Transcript

The Audit Podcast

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

AI summary 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

19:15EnglishSummary · Transcript

Stanford Online

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

AI summary 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)

EnglishSummary · Transcript

More new episodes

All English Chinese
  1. Speech-to-Speech Model Research at Google DeepMind — Valeria Wu Fon & Tom Ouyang, Google DeepMind

    AI Engineer

    Summary17 min
  2. No Memory, No Harness: Why the Database Is the Last Line of Defense — Kay Malcolm, Oracle

    AI Engineer

    Summary22 min
  3. How We Solved Agent Building — Andrew Qu, Vercel

    AI Engineer

    Summary18 min
  4. Agents Without Code: Skills, YAML, and Filesystems Replaced Python — Philipp Schmid, Google DeepMind

    AI Engineer

    Summary18 min
  5. Your Voice Agent is Just a Walkie Talkie — Neil Zeghidour, Gradium

    AI Engineer

    Summary19 min
  6. Voice Agents Can Just Do Things — Charlie Guo, OpenAI

    AI Engineer

    Summary16 min
  7. Tolan: Voice-First AI Companion — Paula Dozsa, Tolan

    AI Engineer

    Summary15 min
  8. 1 Trillion Phone Calls/yr, 10% Error rate: The Crisis in Voice AI — Sumanyu Sharma, Hamming AI

    AI Engineer

    Summary16 min
  9. 5 Voice Agent Failure Modes You'll Hit in Week One — Venky B, Plivo

    AI Engineer

    Summary27 min
  10. Inside the AI Stack of an $8.3B AI Company’s Product Team | Together AI

    The Growth Podcast

    Summary59 min
  11. Speech Recognition Is Not a Solved Problem — Pavan Muddireddy

    Machine Learning Street Talk (MLST)

    Summary01:42:22
  12. Tokens Should Have Jobs — Katelyn Lesse & Angela Jiang, Anthropic

    AI Engineer

    Summary13 min
  13. [人人能懂AI前沿] AI的陪练、地图与慢功夫

    AI可可AI生活

    Summary00:27:28
  14. Harness Engineering: Building the Production Cage for Powerful Domain Agents — Mike Chambers, AWS

    AI Engineer

    Summary21 min
  15. Loophole: Adversarial Agents To Stress Test Your Morality — Brendan Rappazzo, Morgan Stanley

    AI Engineer

    Summary17 min
  16. Every step you take, every call you make: the reliable agent stack — Giselle van Dongen, Restate

    AI Engineer

    Summary21 min
  17. How Grok Bot designers use AI agents to build personal sites and product prototypes | John Bai & Peng Zheng

    How I AI (private feed for hi.fangyuhan@icloud.com)

    Summary42 min
  18. [人人能懂AI前沿] 当AI学会画地图、测信念、搞协作

    AI可可AI生活

    Summary00:28:41
  19. Navier-Stokes and AI generated work: If You Can't Explain It, Did You Really Do It?

    The Data Exchange with Ben Lorica

    Summary56 min
  20. [人人能懂AI前沿] 从AI培训工厂、进化式学习到合作的计算本质

    AI可可AI生活

    Summary00:27:58
  21. FDA hears input on psychedelics, PDUFA, lung cancer’s next-gen therapies boost survival

    BioSpace

    Summary00:22:11
  22. AI:AM Highlights: Astra as AGI, OpenAI's Pause, Mythos @ Mozilla & Human Agency vs Technocapitalism

    "The Cognitive Revolution"

    Summary1 h 42 min
  23. Building ambitious software — Jonathan Kelley, Dioxus Labs & Cognition

    AI Engineer

    Summary19 min
  24. [人人能懂AI前沿] 从自我进化、系统协作到负向学习：AI智能的别样路径

    AI可可AI生活

    Summary00:27:38
  25. Why two promising heart drugs flopped and what's next

    The Readout Loud

    Summary30 min
Podwise

Summaries for every new episode.

Follow your shows in Podwise and read each new episode before you decide to listen.

Start for free Find more in Podwise