Backend | Java | Quarkus | AI | Career
There’s a term making the rounds that you should know: tokenmaxxing. It describes engineers competing to burn AI tokens under employer-imposed usage metrics. The concept exposes something structural about how companies measure AI adoption. Here’s how it works: some companies offer generous token budgets as a recruiting perk. Then they start treating consumption as a … Read more
Three things landed in the enterprise plumbing in the past few weeks. At Knowledge 2026 (May 5), ServiceNow announced Action Fabric, an open MCP (Model Context Protocol) server, building on top of the Now Assist MCP Server Console that has been GA since the Zurich release earlier this year. Jama published its own MCP Server. … Read more
A few years back, the question “compile to native or stay on the JVM?” had a short answer: it depended on whether you needed sub-100ms cold start as part of the SLA. If you did, you went GraalVM Native Image and paid the price in reflection metadata, dynamic class loading limitations, and tooling that was … Read more
A lot of AI coding demos look impressive for about five minutes. Then reality shows up. Reality is the old service nobody wants to touch on a Friday afternoon. Reality is the module with naming debt, historic compromises, and a commit history that reads like a crime scene. Reality is the enterprise Java codebase that … Read more
LLM is CPU. Context window is RAM. Andrej Karpathy captured something real with that analogy: the model processes, but the context is where information lives. What the model can reason about is bounded by what you put in that window, and how you structure it. In 2026, Gartner formally defined context engineering as a core … Read more