In this episode, we discuss the rising cost of using AI and how usage-based pricing, model changes, and capacity limits are affecting daily work as AI moves from experimentation into operational use. We also talk about multi-model workflows, hybrid infrastructure, and examples of using hosted models alongside open models locally for tasks such as writing and named entity resolution. We get into the need for enterprises to run their own AI infrastructure, including questions around GPU pooling, routing, reservation, data sovereignty, and service levels.
Tag Archives: AI
MCP Agents and Context
In this episode, we continue our journey even deeper into how agentic vibe coding and other AI-based automation. This time we focus on Model Control Protocol (MCP) and its application in our bare metal automation solution, Digital Rebar. We examine deterministic versus stochastic AI approaches and the importance of reliable system integration without competing with other agentic systems. We highlight MCP’s role in streamlining interactions across data sources, with a focus on practical applications in finance and infrastructure resilience. The episode ends with a preview of future conversations on user experience transformation in infrastructure operations. Enjoy!
Transcript here: otter.ai/u/LmtQ9QAc79izN0PacE…=transcript&tab=chat
Vibe Coding Mapping [TechOps]
In this episode, we continue our Vibe Coding experiment. Now that we’ve figured out how to interface with MaaS, this time we wrestle with mapping and how different systems interact with each other. We’re joined by Greg Althaus, RackN CTO, who reviews the project and asks some really great questions. We talk about our decision to restart the experiment, taking the lessons we’ve learned to the newer software available. Enjoy!
Transcript: https://otter.ai/u/NohM8_D7DfbUu9iZc1MSpxi00kg?utm_source=copy_url
Vibe Coding for Ops [TechOps]
In this episode, we do some live vibe coding– using AI to write code. We share tips and tricks on having the best vibe coding experience and avoiding some common pitfalls. You’ll get to hear what we do, how we discover what the steps are, just how easy it is to interact with the system, to set up a basic environment. We also start to explore the limitations of vibe coding. We encourage you to listen along and try on your own!
Transcript: otter.ai/u/CqKdtWZWYb3AdPtcb-…?utm_source=copy_url
Infrastructure Summit Debrief
Rich Miller and I debrief our experiences at the AI Infrastructure and Edge Summit in Santa Clara. This show was interesting in the way it combined a lot of different pieces together related to AI. We share our thoughts and critiques on the event’s sales-oriented focus, which overshadowed meaningful discussions on AI applications and data governance.
Transcript: otter.ai/u/5zn42OkdumP-HXIdi5…?utm_source=copy_url
Model Context Protocol Exploration
Today we continue our exploration of vibe coding by digging into the Model Context Protocol, or MCP. We look at how MCPs connect chatbots to backend systems, why natural language matters for complex queries, and what it takes to build smarter, more adaptable interfaces. The discussion covers practical strategies for refining and automating these systems using API docs, making this a solid deep dive into the future of human-to-machine interaction.
Transcript: otter.ai/u/5zn42OkdumP-HXIdi5…?utm_source=copy_url
TechOps Scaling Challenges
In this episode, we talk about scale and the hard realities of system failure in large tech operations. We explore why rare failures become common at scale, and what it takes to build systems that can handle that pressure. From predictive diagnostics to component redundancy, we share practical insights on keeping high-performance and AI infrastructure resilient. This is not theory, it is grounded in real-world lessons from managing complex environments and learning how to plan, isolate, and adapt when things go wrong.
Transcript: otter.ai/u/X8JYiADfPPLEfQ-gge…?utm_source=copy_url
AI Export Controls Work?
We discuss whether or not AI export controls work, but we take a really interesting twist because what we talk about is manufacturing. What we talk about is innovation, and it’s not whether or not you can control AI chips, but what does it actually take to build innovative product? That’s where we really have challenges on export and controls. There’s military manufacturing and goods, and that’s part of what this AI embargo is about. We really talk about how challenging it is to actually build truly innovative manufacturing and what the barriers are.
Transcript: otter.ai/u/k6Thp-TOfwKc_RjXHC…?utm_source=copy_url
Using AI for Complex IT Problems
In this episode, we talk about how to use AI and agentic AI specifically to rethink log collection and analysis, and find and solve really difficult problems generally. There’s a bit of a build up and understanding how we got there will help you appreciate the conversation.
Resources:
www.usenix.org/conference/srecon…presentation/cruz
Transcript: otter.ai/u/P-p1tfjPhD4lbX8cy6…?utm_source=copy_url
AI Slop Ate My College Degree!
Today we riff on vibe coding, and we talk about the human and economic impacts. Can this agentic coding paradigm the use of AI and how will it impact people just starting their careers or building real applications? What is the trajectory for AI, generated systems and code and what is the risk of AI slop?
Transcript: otter.ai/u/5G4AnR858BJnYVZiPV…?utm_source=copy_url