https://drpwchen.com/en/tags/ai/Recent content in AI on Po-Wei Chen, MD — Physiatrist & Builderhttps://drpwchen.com/og-default.pnghttps://drpwchen.com/og-default.pngHugoenFri, 24 Jul 2026 16:30:00 +0800https://drpwchen.com/en/posts/getting-started/Fri, 24 Jul 2026 07:15:00 +0800https://drpwchen.com/en/posts/getting-started/You can follow along even if you've never used the command line: install Claude Code with one command, understand GitHub pages, and get your first open-source tool running and producing results.https://drpwchen.com/en/posts/talking-to-agents/Fri, 24 Jul 2026 06:45:00 +0800https://drpwchen.com/en/posts/talking-to-agents/Getting the tools installed is just the beginning. Three mindsets, four meta-skills you can use right away, how to write prompts now, and what belongs in each of the three layers of constraints for AI.https://drpwchen.com/en/posts/my-ai-toolbox/Mon, 20 Jul 2026 13:15:00 +0800https://drpwchen.com/en/posts/my-ai-toolbox/A complete list of the tools I actually use, categorized by need: AI assistants, speech-to-text, OCR, notes and knowledge base, paper tools, free website hosting, home servers and backup systems, plus the open-source scripts I wrote myself.https://drpwchen.com/en/posts/paper-fetch/Tue, 14 Jul 2026 08:15:00 +0800https://drpwchen.com/en/posts/paper-fetch/To let AI read papers for you, you first need the full text. And what usually gets you stuck isn't the AI—it's permissions, publishers, and the library. paper-fetch uses a step-by-step route from open access, to official publisher APIs, to your own hospital library to turn a DOI into a full-text PDF, without taking any piracy routes.https://drpwchen.com/en/posts/github-bot-marketing/Thu, 09 Jul 2026 10:45:00 +0800https://drpwchen.com/en/posts/github-bot-marketing/My open-source paper tool received a GitHub issue full of sincere praise. After checking, I found it was automated marketing spammed by a bot to 26 repos within two minutes. This post breaks down its tactics, the paid marketplace model behind it, and why running it with your own subscription is a better deal.https://drpwchen.com/en/posts/paper-tools/Tue, 07 Jul 2026 09:30:00 +0800https://drpwchen.com/en/posts/paper-tools/I took the entire workflow of a journal club critical appraisal and wrote it into two Claude Code skills. I even wrote two deterministic little scripts to hand over the calculation of evidence certainty and logical flaws to code, stopping the AI from bullshitting based on overall impressions. It's already open-sourced on GitHub.https://drpwchen.com/en/posts/ai-token-4-budget-dashboard/Mon, 29 Jun 2026 06:30:00 +0800https://drpwchen.com/en/posts/ai-token-4-budget-dashboard/The final part of the saving tokens series: not everything needs the smartest brain, and even for reading images, the cheapest model is often enough. Toss noisy chores to a clone to keep your desk clean, then install a dashboard, or even let the AI watch its own usage and pace the budget just right.https://drpwchen.com/en/posts/ai-token-2-script-vs-llm/Mon, 29 Jun 2026 06:30:00 +0800https://drpwchen.com/en/posts/ai-token-2-script-vs-llm/Some jobs simply shouldn't be given to AI. Clear-cut, repetitive tasks belong to hardcoded scripts—they're fast, accurate, and practically free. Vague, judgment-heavy tasks are what you boot up AI for. Here's how I read my medical textbook PDFs as an example of making this tradeoff.https://drpwchen.com/en/posts/ai-token-3-clean-desk/Mon, 29 Jun 2026 06:30:00 +0800https://drpwchen.com/en/posts/ai-token-3-clean-desk/There's a cost you pay with every sentence: the config file residing right in front of the AI. Keep it lean, layer the memory, make good use of prompt caching to bill repeated content at one-tenth the price, and throw away the noise of successful commands directly. A clean desk doesn't just save money; the AI answers more accurately, too.https://drpwchen.com/en/posts/ai-token-1-chat-gets-dumber/Mon, 29 Jun 2026 06:30:00 +0800https://drpwchen.com/en/posts/ai-token-1-chat-gets-dumber/AI has no memory. With every reply, it rereads the entire conversation from the beginning, which is why longer chats get slower, more expensive, and dumber. This post explains the mechanism using a taxi meter analogy, and gives everyone who chats with AI three ways to save that you can use today.https://drpwchen.com/en/posts/ai-agent-secrets-audit/Sun, 28 Jun 2026 01:30:00 +0800https://drpwchen.com/en/posts/ai-agent-secrets-audit/After handing over permissions to read files, execute commands, and connect to the internet to an AI assistant, I went back to inventory, lock, and revoke my scattered keys and tokens, putting together a few security habits for using AI.https://drpwchen.com/en/posts/vault-graph-rag/Mon, 22 Jun 2026 15:00:00 +0800https://drpwchen.com/en/posts/vault-graph-rag/I threw a new paper on SQL-RAG at Claude to verify it myself: useless for a redundant textbook library, but a great fit for finding "related notes" in a sparse Obsidian medical note vault. After swapping the ranking to personalized PageRank, the proportion of correctly finding related notes jumped from 34% to 84%, and I put it straight into production.https://drpwchen.com/en/posts/rehab-specialist-board-2026/Sat, 20 Jun 2026 18:00:00 +0800https://drpwchen.com/en/posts/rehab-specialist-board-2026/I finished the board examination last weekend and officially became a PM&R attending physician. Looking back at my four years of training at Hualien Tzu Chi Hospital, from Prof. Cifu's reminder to "not be limited", to getting exposure to pediatric rehab, neuro, orthopedics, musculoskeletal ultrasound, and manual therapy, and then jumping into vibe coding with Claude Code this February to redesign my study methods. Documenting this milestone, and previewing the AI learning tools I want to share next.