Castuner

Linear Digressions

Katie Malone

In each episode, your hosts explore machine learning and data science through interesting (and often very unusual) applications. 896520

Web del podcast

Escolta'l a la teva aplicació

Episodis

331 episodis

  1. KV Cache Fundamentals 24:16
  2. AI Inference 101 27:37
  3. Back Next Week 0:18
  4. Back in Two Weeks 0:21
  5. Mechanistic Interpretability: How Researchers Try To See Inside Models 29:21
  6. LLM As A Judge 30:12
  7. The Impact of AI on Podcasting (Harvard Data Science Review Cross-Post) 29:38
  8. Better Know A Benchmark: ExploitGym 32:34
  9. Constitutional AI 31:57
  10. A Data-Driven Reality Check on AI in Business (Interview with Tom Davenport, Babson College) 40:28
  11. Understanding AI Text Watermarking 29:57
  12. Better Know a Benchmark: Humanity's Last Exam 23:21
  13. A Scientific Deep Dive into Overconfident LLMs: Interview with Kaitlyn Zhou (Cornell) 33:54
  14. Reasoning Models: When LLMs Went Beyond Fancy Autocomplete 25:00
  15. Distillation, or, How to Steal a Model 23:38
  16. Invisible LLM Failures and AI Fluency with Chris Potts (Stanford) 41:23
  17. Still summer break: back next week 0:25
  18. Summer break: back soon 0:36
  19. Interviewing the Linear Digressions Agents (The Agents Season, Episode 11) 37:39
  20. Agent Economics (The Agents Season, Episode 10) 24:24
  21. Agent Trust, Oversight and Control (The Agents Season, Episode 9) 25:41
  22. Many Agents, Many Problems (The Agents Season, Episode 8) 28:26
  23. How Do You Evaluate An AI Agent? (The Agents Season, Episode 7) 31:45
  24. AI Agent Failure Modes (The Agents Season, Episode 6) 32:42
  25. Agentic Planning (The Agents Season, Episode 5) 24:00
  26. Memory Management for AI Agents (The Agents Season, Episode 4) 24:41
  27. Lost in the Middle (The Agents Season, Episode 3) 19:44
  28. ReAct and Tool Usage (The Agents Season, Episode 2) 23:41
  29. What's an AI Agent? And Why's That Hard to Define? (The Agents Season, Episode 1) 19:03
  30. Unfaithful Chain of Thought 24:32
  31. Benchmark Bank Heist 12:36
  32. Benchmarking AI Models 29:55
  33. The Hot Mess of AI (Mis-)Alignment 22:32
  34. The Bitter Lesson 19:17
  35. From Atari to ChatGPT: How AI Learned to Follow Instructions 25:53
  36. It's RAG time: Retrieval-Augmented Generation 17:14
  37. Chasing Away Repetitive LLM Responses with Verbalized Sampling 19:12
  38. We're Back 2:58
  39. A Key Concept in AI Alignment: Deep Reinforcement Learning from Human Preferences 19:13
  40. The Impact of Generative AI on Critical Thinking 25:33
  41. So long, and thanks for all the fish 35:44
  42. A Reality Check on AI-Driven Medical Assistants 14:00
  43. A Data Science Take on Open Policing Data 23:44
  44. Procella: YouTube's super-system for analytics data storage 29:48
  45. The Data Science Open Source Ecosystem 23:06
  46. Rock the ROC Curve 15:52
  47. Criminology and Data Science 30:57
  48. Racism, the criminal justice system, and data science 31:36
  49. An interstitial word from Ben 5:59
  50. Convolutional Neural Networks 21:55