<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>ChatGPT on 陳柏威醫師 Po-Wei Chen, MD</title><link>https://drpwchen.com/tags/chatgpt/</link><description>Recent content in ChatGPT on 陳柏威醫師 Po-Wei Chen, MD</description><image><title>陳柏威醫師 Po-Wei Chen, MD</title><url>https://drpwchen.com/og-default.png</url><link>https://drpwchen.com/og-default.png</link></image><generator>Hugo</generator><language>zh-TW</language><lastBuildDate>Mon, 29 Jun 2026 06:30:00 +0800</lastBuildDate><atom:link href="https://drpwchen.com/tags/chatgpt/index.xml" rel="self" type="application/rss+xml"/><item><title>我幫 AI 裝了一個省錢儀表板</title><link>https://drpwchen.com/posts/ai-token-4-budget-dashboard/</link><pubDate>Mon, 29 Jun 2026 06:30:00 +0800</pubDate><guid>https://drpwchen.com/posts/ai-token-4-budget-dashboard/</guid><description>省 Token 系列完結篇：不是每件事都需要最聰明的腦袋，連看圖很多時候最便宜的模型就夠用。把吵鬧的雜事丟給分身保持桌面乾淨，再裝一個儀表板，甚至讓 AI 自己盯著用量、照節奏把預算用到剛好。</description></item><item><title>為什麼你的 AI 越聊越慢、越聊越笨？</title><link>https://drpwchen.com/posts/ai-token-1-chat-gets-dumber/</link><pubDate>Mon, 29 Jun 2026 06:30:00 +0800</pubDate><guid>https://drpwchen.com/posts/ai-token-1-chat-gets-dumber/</guid><description>AI 沒有記憶，每次回覆都把整段對話重讀一遍，所以對話越長越慢、越貴、也越笨。這篇用計程車跳表的比喻講清楚原理，給每個用 AI 聊天的人三個今天就能用的省法。</description></item></channel></rss>