TheBitCast

Pop Goes the Stack

Autor: F5

Explore the evolving world of application delivery and security. Each episode will dive into technologies shaping the future of operations, analyze emerging trends, and discuss the impacts of innovations on the tech stack.

Odcinki

  1. AI governance: Shadow AI, real access, real risk – Pop Goes the Stack
  2. AI broke your app? It’s probably DNS (Again) – Pop Goes the Stack
  3. Agentic fingerprints: Detect, debug, and control AI traffic – Pop Goes the Stack
  4. AI code quality management: Guardrails, hooks, and Open Source – Pop Goes the Stack
  5. AI API Security: Same toolbox, new scale and new risks – Pop Goes the Stack
  6. Stop “securing the model”—Secure the runtime instead – Pop Goes the Stack
  7. What actually is Model Routing? A deep dive into cost, efficiency & risk – Pop Goes the Stack
  8. AI traffic management: Load balancing vs model routing – Pop Goes the Stack
  9. Agents go rogue: Why guardrails fail and behavior wins – Pop Goes the Stack
  10. If your agent buys it, you bought it: Liability in AI – Pop Goes the Stack
  11. AI blast radius: BOLA + MCP turned APIs into a 7,000-bot army – Pop Goes the Stack
  12. Epic AI fails: Why “useful” isn’t “correct” – Pop Goes the Stack
  13. Does your chatbot code? Why guardrails fail (and how to fix drift) – Pop Goes the Stack
  14. The Great AI Repatriation: Why Cloud‑Only LLMs break the budget – Pop Goes the Stack
  15. Training vs Inference: Are they the same? – Pop Goes the Stack
  16. Round Robin is Still Dumb: Load balancing has to grow up for AI inference – Pop Goes the Stack
  17. Mechanistic Interpretability: Debugging LLMs by reading their circuits – Pop Goes the Stack
  18. Pop Goes the Stack will be back next week! – Pop Goes the Stack
  19. Agent Skills: The new AI supply chain risk (and fixes) – Pop Goes the Stack
  20. Is AI making security obsolete? – Pop Goes the Stack
  21. Agents deleted my work: Why agents still aren’t ready for production (Yet) – Pop Goes the Stack
  22. Agent identity: Closing the "accountability vacuum" with humans – Pop Goes the Stack
  23. Data poisoning: You can’t patch what an LLM “learns” – Pop Goes the Stack
  24. Local-first AI: Keep context out of the cloud – Pop Goes the Stack
  25. DevOps meets AI agents: Risk, audit, and the Deming playbook – Pop Goes the Stack
  26. Model routing isn’t load balancing (And that’s why you’re not ready) – Pop Goes the Stack
  27. KV cache is the real inference bottleneck (Not GPUs) – Pop Goes the Stack
  28. Measuring what matters: Observability for agents – Pop Goes the Stack
  29. Alien autopsy of LLMs: Constitutions, deception, guardrails – Pop Goes the Stack
  30. Why Prompt Filters Fail Against LLM Attacks – Pop Goes the Stack