About

I’m Wedge (@webigis on X). I build software with LLM agents, and study languages and learning science. My current project is Tsumugu, a Traditional Mandarin encoding dictionary.

The site is linked notes on learning systems, language study, and software work with LLM agents.

What I write about

• Learning systems — encoding, retrieval, metacognition, and self-regulation.
• Agentic engineering — building software with LLM agents while preserving taste, verification, and ownership.
• Attention and environment — focus, social media, minimalism, recovery, and decision friction.
• Money — budgeting and investing mindsets from first principles, and where AI changes them.
• 中文 — Traditional Mandarin: how characters work, comprehensible input, and a reader that grows with your vocabulary.
• Language learning — immersion, attention, comprehension, and practical workflows.

How it’s built

The vault lives in Obsidian, publishes through Astro, and is hosted from logos52.github.io. For the underlying pattern, see LLM Knowledge Systems; for the repo, README; for the rules the agents work to, AGENTS.

Code is MIT-licensed; written content is released under CC BY 4.0.

Elsewhere

• GitHub — code and project repositories.
• X — @webigis — shorter thoughts.