Build Your Workflow

While redesigning this space where I write and think, I came across a post from Andrej Karpathy that captures exactly what I want to explore here:

"I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. I have a sense that I could be 10X more powerful if I just properly string together what has become available over the last ~year and a failure to claim the boost feels decidedly like skill issue. There's a new programmable layer of abstraction to master (in addition to the usual layers below) involving agents, subagents, their prompts, contexts, memory, modes, permissions, tools, plugins, skills, hooks, MCP, LSP, slash commands, workflows, IDE integrations, and a need to build an all-encompassing mental model for strengths and pitfalls of fundamentally stochastic, fallible, unintelligible and changing entities suddenly intermingled with what used to be good old fashioned engineering. Clearly some powerful alien tool was handed around except it comes with no manual and everyone has to figure out how to hold it and operate it, while the resulting magnitude 9 earthquake is rocking the profession. Roll up your sleeves to not fall behind."

— Andrej Karpathy

This resonates deeply. The programming landscape has shifted, and the gap between those who adapt and those who don't is widening fast.

Research and Study as Part of the Workflow

A core component of any effective workflow is the research and study phase. The challenge lies in capturing both the types of research you do and the content you consume, then organizing these notes into something useful.

Let's try this approach: build a system that historicizes everything in markdown, allowing me to study and reference directly from my development environment. As I read and learn, I reorganize notes in my vault, creating a living knowledge base that grows alongside my skills.

I don't want to get stuck on a single book or source, but I also don't want to lose track of where I am in studying a particular resource. The system needs to support both flexibility and continuity, letting me jump between sources while maintaining context and progress on each one.

The challenge is clear: multiple sources, multiple formats, multiple types of content. The solution is to build a tool that standardizes all knowledge, starting from markdown. This creates a unified foundation where everything can be processed, searched, and connected regardless of its original form.

One of the key problems I need to solve is the method for acquiring knowledge efficiently. I want to explore broadly, horizontally, accumulating understanding across many domains until something naturally pulls me deeper into a specific topic or an intersection between fields. The question becomes: what is the right mental setting, the right workflow, that keeps me in the flow of effective learning?