https://drpwchen.com/en/tags/ai-workflow/Recent content in AI Workflow on Po-Wei Chen, MD — Physiatrist & Builderhttps://drpwchen.com/og-default.pnghttps://drpwchen.com/og-default.pngHugoenSat, 25 Jul 2026 06:45:00 +0800https://drpwchen.com/en/posts/claude-pacer/Sat, 25 Jul 2026 06:45:00 +0800https://drpwchen.com/en/posts/claude-pacer/The most common way for AI to die running tasks autonomously at night isn't bad code, it's hitting the usage limit and getting cut off. claude-pacer solves this with a three-layer design: a status line for humans, a budget alert for AI, and a GO/PACE/STOP verdict for agents to run. Open source MIT.https://drpwchen.com/en/posts/note-supplement/Thu, 23 Jul 2026 06:45:00 +0800https://drpwchen.com/en/posts/note-supplement/My note vault has only one rule: one note per topic. If the same thing is covered in five different places, it's the same as having no notes. The hard part is holding this line as sources pile up. note-supplement handles merging outside materials back into existing notes, without breaking the things you already got right.https://drpwchen.com/en/posts/textbook-to-note/Sun, 19 Jul 2026 15:45:00 +0800https://drpwchen.com/en/posts/textbook-to-note/With over forty designated reference books for the board examination, and the same concepts scattered across multiple books, how could anyone possibly finish reading them? I tuned AI to my note-taking workflow, letting it organize textbooks structurally and with evidence. Today I open-sourced the whole setup, and this post covers the five hurdles I cleared along the way.https://drpwchen.com/en/posts/my-data-my-benchmark/Mon, 13 Jul 2026 16:31:00 +0800https://drpwchen.com/en/posts/my-data-my-benchmark/MediaTek's official benchmark already proves Breeze-ASR-25 beats Whisper, but it isn't testing your task. Using a 180,000-word glossary built from hundreds of textbooks as a yardstick, I found it captures 49% more real vocabulary and runs faster. Another finding not in any model card: the time alignment of the Taiwanese version, Breeze-ASR-26, has regressed. Default decoding only segments once every 30 seconds, which outright breaks when making subtitles or aligning with slides, but enabling word-level timestamps saves it. The testing method is open-sourced.