Create a powerful "second brain" by consolidating your podcasts, newsletters, and other content into a single markdown file. This plain-text document is easily consumed by AI agents, training them on your specific knowledge, tone, and frameworks. This allows the AI to generate outputs that are filtered through your unique expertise.

Build a system where new data from meetings or intel is automatically appended to existing project or person-specific files. This creates "living files" that compound in value, giving the AI richer, ever-improving context over time, unlike stateless chatbots.

While tokens are an LLM's energy source, structured markdown files in a system like Obsidian act as its perfect, persistent memory. This organized, interlinked data is the true "oxygen" that allows an AI to develop a deep, evolving understanding of your context beyond single-session interactions.

LLMs learn two things from pre-training: factual knowledge and intelligent algorithms (the "cognitive core"). Karpathy argues the vast memorized knowledge is a hindrance, making models rely on memory instead of reasoning. The goal should be to strip away this knowledge to create a pure, problem-solving cognitive entity.

To maximize an AI assistant's effectiveness, pair it with a persistent knowledge store like Obsidian. By feeding past research outputs back into Claude as markdown files, the user creates a virtuous cycle of compounding knowledge, allowing the AI to reference and build upon previous conclusions for new tasks.

AI development environments can be repurposed for personal knowledge management. Pointing tools like Cursor at a collection of notes (e.g., in Obsidian) can automate organization, link ideas, and allow users to query their own knowledge base for novel insights and content generation.

By storing all tasks and notes in local, plain-text Markdown files, you can use an LLM as a powerful semantic search engine. Unlike keyword search, it can find information even if you misremember details, inferring your intent to locate the correct file across your entire knowledge base.

Instead of explicitly telling an AI agent how to organize its knowledge, simply provide the necessary context. A well-designed agent can figure out what information is important and create its own knowledge files, such as a 'user.md' for personal details or an 'identity.md' for its own persona.

Build a repository of small, functional tools and research projects. This 'hoard' serves as a powerful, personalized context for AI agents. You can direct them to consult and combine these past solutions to tackle new, complex problems, effectively weaponizing your accumulated experience.