The conceptual foundation of OpenML dates all the way back to 2013 when a college boy in Physics major was reading and implementing the Matrix Numerov Method for Solving Schrödinger Equation

Why would AI work? Certainly technological advancements and market conditions have their contributions. But it is the philosophical justification presented by one of the greatest philosophers, David Hume, that has made it inevitable which this post shows by examining and linking his most phenomenon work - "An Enquiry Concerning Human Understanding"

In this post, we explore the core architectural philosophy behind OpenML's backend infrastructure: a deliberate choice of explicit control and standards compliance over framework magic. By anchoring our microservices to the strict rules of the JAX-RS specification, and leveraging precise engines like Jersey and Quarkus rather than comprehensive ecosystems like Spring, we ensure our codebase remains portable and maintain absolute sovereignty over our entire execution environment.

Just as DevOps brought structure to software deployment and MLOps did the same for training models, AgentOps is the emerging field dedicated to the lifecycle of agentic AI. Shared evaluation frameworks like Harbor is an example of AgentOps. The core philosophy driving this shift is moving away from "walled-garden" testing (where companies build private tests that happen to make their own agents look good) toward Standardized Evaluation Environments. It is the realization that a benchmark is only trustworthy if everyone can run it, inspect it, and use the exact same ruler to measure success.

Looking at OpenJDK from both technical and business perspective

When I tried to package a standard agent skill with image assets into a MCP server and an agent can't see or fetch those images through MCP, because MCP protocol (modelcontextprotocol.io) does not contain any specification or protocol standard regarding how an MCP server should deliver or serve an assets folder from skill (agentskills.io), I sensed a fundamental mismatch between skill and MCP which triggered this blog post