All Episodes
Displaying 1 - 20 of 45 in total
Local-first AI: Keep context out of the cloud
“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 Stack, Lori MacVitti...
DevOps meets AI agents: Risk, audit, and the Deming playbook
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. incident. In this episode...
Model routing isn’t load balancing (And that’s why you’re not ready)
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 Joel Moses dig into f...
KV cache is the real inference bottleneck (Not GPUs)
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, Lori MacVittie sit...
Measuring what matters: Observability for agents
Agents break the old rules of observability. Latency, throughput, and error rates still matter, but once software starts making decisions and taking actions on someone...
Alien autopsy of LLMs: Constitutions, deception, guardrails
Why do researchers keep describing large language models like aliens? Because in enterprise environments, they often behave like something we didn’t build and can’t fu...
Why Prompt Filters Fail Against LLM Attacks
Prompt injection has been the headline security problem for the last year, but have we been guarding the wrong layer? Lori MacVittie is joined by cohost Joel Moses and...
OpenClaw: Multi-agent autonomy, secrets, and blast radius
OpenClaw is what happens when the industry looks at autonomous agents and decides they should have more autonomy, more persistence, and more chances to surprise you. I...
CISO Hot Takes on MCP, PQC, and Data Center Attacks
Recorded live at F5 AppWorld 2026 in Las Vegas, this episode of Pop Goes the Stack puts Field CISO Chuck Herrin in the hot seat for a fast-moving conversation on what ...
AI Red Teaming in Practice: Scores, guardrails, auto-remediation
AI in production isn’t just another feature to ship. It’s a non-deterministic system that can be socially engineered, fuzzed, and pushed into failure states you won’t ...
Agent Identity Crisis: Access, audit, and “soul.md”
Coming to you from the AppWorld show floor, Joel Moses and guest co-pilot Oscar Spencer cut through the conference polish to tackle a problem that’s quickly becoming u...
VibeOps: Guardrailed agents for deterministic production
Ops used to be a world of YAML, caffeine, and careful deploy rituals. Now it’s probabilistic models, token-based cost surprises, and reliability questions that sound m...
WebAssembly: A programmability paradigm shift
Programmability is experiencing a paradigm shift, and this episode explains why WebAssembly is at the center of it. F5's Lori MacVittie and Joel Moses are joined by We...
Unstructured Integration: The hidden surface area putting AI privacy & compliance at risk
"It's just a chat" is the most dangerous sentence in AI. In this episode of Pop Goes the Stack, F5's Lori MacVittie and Joel Moses are joined by data science expert Sc...
Logging for Giants: High-Speed Telemetry in an AI World
When OpenAI discovered they could reclaim 30,000 CPU cores simply by tuning the log-forwarding agent Fluent Bit—disabling a single function that ate ~35 % of one serve...
Low-Code Automation Tools with Teeth: FlowFuse & N8N
Low-code automation has grown up, and the competition is getting spicy. In this episode of Pop Goes the Stack, F5's Lori MacVittie and Joel Moses are joined by Aubrey ...
The New New User Interface: AI in your brain
The capability to map brain activity to language isn’t just another UI shift—it’s a paradigm shift in how humans and machines might communicate. If you’re building sys...
The Impact of Inference: Reliability
Traditional reliability meant consistency. Given identical inputs, systems produced identical outputs. Costs were stable and behavior predictable. Inference reliabilit...
The Impact of Inference: Performance
Traditional performance meant deterministic response times. Identical inputs produced near-identical execution times. Optimizations reduced latency, but variance was m...
The Impact of Inference: Availability
What does "availability" mean in a world of AI inferencing and ever-shifting workloads? It’s no longer just about servers responding or apps being online—availability ...