Podcast Episodes
Back to SearchIs AI making security obsolete?
Episode 46
What happens if AI finally writes secure code by default? In this episode of Pop Goes the Stack, F5's Lori MacVittie, Joel Moses, and Ken Arora take …
4 months, 2 weeks ago
Agents deleted my work: Why agents still aren’t ready for production (Yet)
Episode 45
An agent deleting a production database (and the backups) isn’t a sci-fi failure. It’s a boundary failure, and it starts with a human handing out cre…
4 months, 3 weeks ago
Agent identity: Closing the "accountability vacuum" with humans
Episode 44
Identity used to be straightforward: authenticate a user, authorize an action, log the request, and move on. Agentic systems complicate that model be…
5 months ago
Data poisoning: You can’t patch what an LLM “learns”
Episode 43
If you’ve been treating “garbage in, garbage out” as a metaphor, this episode turns it into a live-fire scenario. Lori MacVittie and Joel Moses are j…
5 months, 1 week ago
Local-first AI: Keep context out of the cloud
Episode 42
“Just throw it in the cloud” gets complicated when the data is your meetings, your IP, and your operating context. In this episode of Pop Goes the St…
5 months, 2 weeks ago
DevOps meets AI agents: Risk, audit, and the Deming playbook
Episode 41
AI is no longer a lab tool; it’s showing up in pipelines, production systems, and the places where “seemed like a good idea” becomes a 2 a.m. inciden…
5 months, 3 weeks ago
Model routing isn’t load balancing (And that’s why you’re not ready)
Episode 40
Multi-model AI isn’t a buzzword anymore, it’s how organizations are actually operating. In this episode of Pop Goes the Stack, Lori MacVittie and Joe…
6 months ago
KV cache is the real inference bottleneck (Not GPUs)
Episode 39
GPUs get all the attention, but in inference, the real bottleneck is often memory, specifically the KV cache. In this episode of Pop Goes the Stack, …
6 months, 1 week ago
Measuring what matters: Observability for agents
Episode 38
Agents break the old rules of observability. Latency, throughput, and error rates still matter, but once software starts making decisions and taking …
6 months, 2 weeks ago
Alien autopsy of LLMs: Constitutions, deception, guardrails
Episode 37
Why do researchers keep describing large language models like aliens? Because in enterprise environments, they often behave like something we didn’t …
6 months, 3 weeks ago