Exploring the echoes reverberating through time left by the technology of yesterday as we embrace the technology of tomorrow.
AI services need a catalog the same way every other internal platform does. The wiki approach falls over the moment you have more than a handful of models. Backstage with a thin AI plugin layer is the pattern that holds, a direct callback to the catalog discipline.
The interesting work in any AI system lives in the model and the application layer. The boring middleware between them, auth, rate limits, retries, logging, request shaping, is what makes the system actually work. Worth defending the boring part.
After tuning a lot of prompts across my own workflows and reading deeply across the public corpus, the ratio that keeps holding is roughly 30% prompt instructions to 70% retrieved context. The opposite ratio is what most people start with. Worth being plain about why and when to break the rule.
Two hours of chasing a bug that wasn't where the agent said it was, in a file the agent confidently described and that didn't exist. A close reading of one of the more useful failures of the year.
Three platforms running the same models on the same prompts. The Studio numbers are mine; the 5090 and Threadripper numbers are well-published comparables. The takeaway isn't which one wins, it's that the answer depends on which workload you actually have.
DeepSeek shipped R2 with open weights, MIT-licensed, frontier-competitive on the benchmarks that matter, and at a price floor that puts more downward pressure on closed-frontier pricing than anything since R1 in January. The asterisks are gone.
Two and a half years ago I wrote a piece arguing personal AI would be the durable category, not enterprise chatbots. The 2025 version of that bet is partway right and wrong in interesting ways. Worth being clear about what landed and what didn't.
If your AI infra depends on third-party container images, you don't control your supply chain. Forgejo on store-01 as the source-of-truth git host, Harbor on engine-01 as the registry plus image-signing layer. The sovereign-infra argument, and why mirroring is non-negotiable now.
OPA and Rego had a quiet decade as the policy-as-code layer for Kubernetes and IaC pipelines. The AI agent wave is making them load-bearing in a way they weren't before. The renaissance is real and the reasons are structural.
The AI security track at Black Hat this year was the most-attended track. The substance under the hype was a real category forming, prompt injection, model exfiltration, agent privilege abuse, that maps closer to 2014 cloud security than anyone wants to admit.
Not every AI workload belongs on Kubernetes. Some belong nowhere else. The patterns that hold up, separating CPU and GPU tiers, sizing autoscaling for serving versus batch, picking the right foundation, and the ones that fall apart at the first real load.
Cloud lock-in in 2010 was bad. AI lock-in in 2025 is worse for reasons most teams aren't thinking about. The data, the prompt patterns, the agentic surface, the fine-tunes, none of it ports cleanly. Worth being clear about why before you commit.
