Posts

Recently I was spending time with an older adult, and he said to me: “Life really doesn’t need to be that long. I’m already in my 80s, why would I still go exercise and work out? I already go out and walk several times a day, that’s already very good!” Honestly, the first half—“life doesn’t need to be that long”—stumped me. That’s a question about the meaning of life, not something I can answer in a few sentences in clinic. But the second half—“walking several times is enough”—happens to be my own specialty, and I’m confident about this: walking is great, but for an 80-something older adult, relying just on walking really isn’t quite enough. I’ll start from here in the rest of this post. ...

When I shared my critical appraisal tool a while ago (to have Claude help with critical appraisal and summarizing content), a friend gave me a very honest reply: the tool is nice, but having to dig up the PDF yourself every single time is actually the most annoying part. It really is. To let AI read papers for you, you first need the full text. And when it comes to getting the full text, what usually gets you stuck isn’t the AI—it’s permissions, publishers, and the library. ...

Introduction: Why official scores aren’t enough My workflow for turning recorded lectures into notes goes in a straight line: transcript → matching slides → final summary. The foundation of this line is automatic speech recognition (ASR). However much it mishears, every subsequent layer of notes will be just as wrong. Originally, I was using OpenAI’s Whisper large-v3. The starting point for all this was actually me scrolling on my phone and seeing MediaTek Research announce their Taiwanese model, Breeze-ASR-26. A Taiwanese model is intriguing enough on its own, but clicking through, I learned they had already released Breeze-ASR-25 last year. Fine-tuned from Whisper-large-v2, it was optimized specifically for Taiwanese Mandarin and Mandarin-English code-switching, and open-sourced under Apache 2.0. Medical lectures happen to be ground zero for Mandarin-English code-switching. I had somehow missed this for a whole year. ...

The paper tool paper-review-and-digest I shared earlier had only been open-sourced for a few days when it received its first GitHub issue! I was actually quite happy to get my first issue, and I was even more surprised when I opened it: they didn’t just read my code, but accurately pointed out the parts of the design I was most proud of. He said he appreciated the “hard split between the model and deterministic checks”: grade_judge.py doesn’t trust the level of evidence reported by the model itself, but recalculates it from the downgrade items; argdown_lint.py catches argumentative leaps like “jumping from surrogate endpoints to hard endpoints.” Then he said he built an online portal for me, so visitors don’t need to install Claude Code and can just upload a PDF to run the critical appraisal workflow. He even made a promotional image: ...

The paper learning station I shared earlier had “Quality” and “Content” buttons, but I didn’t release the backend implementation back then. It was basically a platform with a frontend web page, but you still had to organize the backend yourself. But for my own setup, of course the backend still had to be wired to AI to reduce the cognitive load. So here I’m sharing those two backend skills to help speed up everyone’s learning! ...

While prepping for the PM&R board examination, I used an engineer’s approach to solve an old problem for myself: how exactly should I practice past exam questions so I don’t forget them right after? I ended up building a small tool called “Exam Navigator,” and figured I’d tidy it up and open it up to share with anyone who needs it. 🔗 Live Demo (built-in demo account, ready to play): https://exam-demo.drpwchen.com 🔗 Source code: https://github.com/drpwchen/exam-practice ...

A while back, I shared the paper reading site I built for myself, and I got quite a few messages asking, “Can I use this too?” and “How exactly does it work?” I’ll explain it clearly in this post, and while I’m at it, I’ll let you know that I’ve organized it into an open-source version and put it on GitHub. First, the problem I wanted to solve. As a physiatrist, there are dozens of journals I want to track, along with a few authors I really want to follow and a couple of topics I’m always keeping an eye on. The traditional approach is to dump a bunch of RSS subscriptions into a reader or a notes app. As a result, hundreds of papers pile up every day, and it quickly turns into a garbage dump of “I’ll never finish reading this, and I don’t even know where to start.” In the end, you either get anxious or just give up reading altogether. ...

📖 Saving Tokens series (four parts): Part 1: Why your AI gets dumber the more you chat · Part 2: Don’t boot up a supercomputer if an abacus will do · Part 3: Setting up a clean desk for your AI · Part 4 (this post, the finale) We’ve arrived at the final post of the series. Over the first three parts, we went from “why your AI gets dumber the more you chat” all the way to “when not to use AI” and “how to clean up its desk.” This post is about the moment you actually spend the money: how to make every penny count. ...

📖 Token Saving Series (4 parts): Part 1: Why your AI gets dumber the longer you chat · Part 2 (This post) · Part 3: Clearing a clean desk for your AI · Part 4: I built a budget dashboard for my AI In the previous post, we talked about how longer AI chats get more expensive and dumber, along with three ways to save right now. This post takes it a step further to discuss a more fundamental divide: ...

📖 The Token Saving Series (4 parts): Part 1: Why your AI gets dumber the more you chat · Part 2: If an abacus works, don’t boot up a supercomputer · Part 3 (This post) · Part 4: I built a budget dashboard for my AI The first two posts were still at the “everyone can use this” level. Starting with this one, I’ll show you the setup on my computer that I’ve endlessly tinkered with. ...