Pop Goes the Stack Por: 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. 57 episodios disponibles Is this your podcast? Claim it Latest episodes of the podcast Pop Goes the Stack Epic AI fails: Why “useful” isn’t “correct” 18/08/2026 Does your chatbot code? Why guardrails fail (and how to fix drift) 11/08/2026 The Great AI Repatriation: Why Cloud‑Only LLMs break the budget 04/08/2026 Training vs Inference: Are they the same? 28/07/2026 Round Robin is Still Dumb: Load balancing has to grow up for AI inference 21/07/2026 Mechanistic Interpretability: Debugging LLMs by reading their circuits 14/07/2026 Pop Goes the Stack will be back next week! 07/07/2026 Agent Skills: The new AI supply chain risk (and fixes) 30/06/2026 Is AI making security obsolete? 23/06/2026 Agents deleted my work: Why agents still aren’t ready for production (Yet) 16/06/2026 Agent identity: Closing the "accountability vacuum" with humans 09/06/2026 Data poisoning: You can’t patch what an LLM “learns” 02/06/2026 Local-first AI: Keep context out of the cloud 26/05/2026 DevOps meets AI agents: Risk, audit, and the Deming playbook 19/05/2026 Model routing isn’t load balancing (And that’s why you’re not ready) 12/05/2026 KV cache is the real inference bottleneck (Not GPUs) 05/05/2026 Measuring what matters: Observability for agents 28/04/2026 Alien autopsy of LLMs: Constitutions, deception, guardrails 21/04/2026 Why Prompt Filters Fail Against LLM Attacks 14/04/2026 OpenClaw: Multi-agent autonomy, secrets, and blast radius 07/04/2026 1 2 3 Next Última »