Context engineering trick: feed LLMs only what changed, via Obsidian edit snapshots
thejaan · x · 2026-09-24
Jaan Altosaar shares his context engineering trick: high-quality LLM output doesn't come from feeding the model all your notes, but only what changed — think track changes. He uses Obsidian, which already snapshots every edit, and built a plugin that compiles a week of those edits into a single file that any LLM can consume to surface connections across his journals.
More from coding & agent
- Anthropic made claude.ai 3x faster in two weeks — and shares how, prompts included — bcherny · 2026-09-24
- Walkthrough: Blender MCP plus FLORA for precise product turntable animations — round · 2026-09-24
- New video series on agent evals kicks off with episode 1: how to read traces — doesdatmaksense · 2026-09-24
- Open-source agent lead-enrichment stack Jev+Treg undercuts Clay at $0.029 per verified lead — cneuralnetwork · 2026-09-24
- uv author: metadata-free lockfiles still detect stale resolutions — charliermarsh · 2026-09-24
- Running Claude vs Codex debates in a shared doc works, but it's slow and expensive — kshitizsriv · 2026-09-24