AI in Obsidian: how I actually use it
No plugin stack – Obsidian holds plain markdown files and Claude works on the same files. A science writer’s daily capture, retrieval, and writing setup.
AI in Obsidian: how I actually use it Read More »
No plugin stack – Obsidian holds plain markdown files and Claude works on the same files. A science writer’s daily capture, retrieval, and writing setup.
AI in Obsidian: how I actually use it Read More »
AI writing detectors flag real writers. A science writer on why detection fails, the tells that actually matter, and how to prove your work is yours.
AI writing detectors and false positives: what the tools get wrong Read More »
One subscription, everything else canceled. A science writer’s honest math on what Claude Max replaces, what it costs, and the client job that paid for it.
What I actually pay for AI (and what I canceled) Read More »
A science writer’s LLM wiki: memory files, Claude Code, an Obsidian vault, and the rule that nothing ships unread. The system for an AI that knows your work.
How I built an AI that actually knows my work Read More »
Full disclosure: AI drafts every post on this blog, from briefs full of my receipts. Here’s the division of labor, and what would make a post not mine.
These posts were drafted by AI. Here’s why they’re still mine. Read More »
AI hallucinations haven’t gone away. A science writer on catching them: the citation trap, the pushback test, and the question to ask every time.
AI hallucinations: why your AI lies to you and how I catch it Read More »
I used Claude Cowork daily, hit three specific walls, and switched to Claude Code. Who should stay, who should switch, and what it really costs.
I tried Claude Cowork and switched to Claude Code – an honest comparison for non-coders Read More »
Vibe writing is drafting by voice: you tell the story, an AI shapes it, you verify every line. How the method works, and what it won’t do.
Vibe writing: how these posts actually get made Read More »
Long AI sessions rot. The decision tree for compact vs handoff vs subagent – what each move preserves, what it loses, and the auto-compact trap.
Claude compact vs. handoff: the decision tree for long sessions Read More »
I’m not a coder. I copied Karpathy’s wiki idea anyway – through eaten workdays, zombie decisions, and one safety-filter wall. The honest build story.
How my AI wiki actually got built (wrong turns included) Read More »