Castuner
Submit a podcast

System Prompt

Peter

System Prompt is a podcast about what’s actually happening in AI.

Not hype. Not surface-level takes.

We break down how AI is changing software, SaaS, infrastructure, and the way systems are built focusing on real-world tradeoffs, architecture decisions, and where the value is actually shifting.

If you’re building, deploying, or thinking seriously about AI, this is for you.

Podcast website

Listen in your app

Episodes

32 episodes

  1. How to Pick the Right AI Model? 41:20
  2. Setting Up Hermes Agent: From Configuration to Automation 48:08
  3. Anatomy of an AI Agent 54:55
  4. AI Is Making SaaS Optional 57:32
  5. Before You Host AI Locally, Watch This 1:04:31
  6. Before You Buy AI Hardware, Watch This 51:57
  7. Your AI Isn’t Dumb. It’s Missing Context. 36:27
  8. The Reality of Physical AI w/ Hiten Sonpal 46:57
  9. NVIDIA, Asana, and New Models 52:58
  10. AI, Accountants, and the Future of the Profession 49:07
  11. Why China is winning the AI race (Qwen3.8:27B is amazing) 53:35
  12. Evals: How Do You Know Which AI Model to Trust? 41:12
  13. Conversation about Quantization(Also about hosting DeepSeekv4:Flash) 42:01
  14. This Is Why Copilot Adoption Is Failing 1:03:16
  15. Your Company Bought AI. Why Isn’t Anyone Using It? 48:49
  16. How AI is Transforming Food Discovery with Stupid Good AI 52:18
  17. Enterprise AI Training Is Failing Because Tool Training Is Not Enough 41:08
  18. What Fable 5’s Removal Reveals About AI Model Dependence 35:15
  19. AI Security Goes Beyond Prompt Injection 54:07
  20. Model Routing Is the Hidden System Behind Reliable AI Applications 32:38
  21. The AI Hardware Shift: When Local Inference Starts Making Business Sense 43:16
  22. AI in Regulated Industries: Compliance, Liability, and Innovation with Joe Ewing 46:59
  23. AI-Native Products Still Need Traditional Software Engineering 46:41
  24. Before You Add AI, Make Sure It Solves the Right Business Problem 39:02
  25. Everyone Says “Just Use RAG.” Here’s Why That’s Not Enough 50:32
  26. Are AI Models Getting Worse, or Are the Economics Catching Up? 40:03
  27. AI Ethics Is Not Just About the Model, It Is About How We Use It 40:23
  28. Physical AI Is Coming, but It Still Struggles Outside Controlled Environments 35:07
  29. AGENTIC CODING IS NOT A TOOL UPGRADE, IT CHANGES THE DEVELOPMENT WORKFLOW 36:51
  30. Are AI Agents Really Taking Jobs, or Changing the Work? 51:07
  31. LOCAL VS. FRONTIER AI MODELS: WHAT SHOULD BUSINESSES ACTUALLY USE? 50:06
  32. Will AI Agents Replace SaaS, or Change Who Builds Software? 43:31