Ming's Spell Compendium #2 -- You Terrifying Upright Apes Are Underestimating Yourselves

This is a cultural adaptation — not a literal translation — of the original Chinese article. Some Chinese cultural references have been swapped for Western equivalents that hit the same emotional note. Previously on… Ming’s Spell Compendium #1 – One Year of Vibe Coding: A Cold Hard Look Foreword Humans, you’re selling yourselves short. How Much Can AI Amplify You? Last year (2024), my working hypothesis was: even with AI, you can’t dramatically exceed the user’s own ability. If AI’s training data represents the sum total of human knowledge, then the current crop of agentic evangelists would have you believe that professional expertise has become a worthless commodity in this era — because AI can write code like Linus, write novels like Hemingway, etc. ...

2026-02-24 · 26 min · ming yang

明系魔法吟唱之2 -- 恐怖直立猿们,你们低估了自己的智慧

英文文化适配版: You Terrifying Upright Apes Are Underestimating Yourselves (English cultural adaptation) 书接上回: 明系魔法吟唱之1 – Vibe Coding 一年实践后的冷思考 前言 人类,你们过于低估自己了。 AI 能放大你多少? 去年(2024)我有个判断是,即便有 AI,也不能大幅超越使用者的能力。如果 AI 的训练知识是全人类知识的总集,现在 agentic 导师们宣传的是在这个时代专业技能变成了唾手可得的不值钱的东西,理由是 AI 可以模仿 Linus 来写代码,也可以模仿大文豪作家写小说,等等。 ...

2026-02-24 · 21 min · ming yang

Ming's Spell Compendium #1 -- One Year of Vibe Coding: A Cold Hard Look

This is a cultural adaptation — not a literal translation — of the original Chinese article. Some Chinese cultural references have been swapped for Western equivalents that hit the same emotional note. Foreword Over the past year I’ve burned through more than $10,000 in API tokens across Google, Anthropic, and OpenAI. So everything in this article is based on hands-on experience with the strongest models available — Opus 4.6, Codex-5.3-xhigh, Gemini 3 Pro — used without budget constraints. ...

2026-02-06 · 20 min · ming yang

明系魔法吟唱之1 -- Vibe Coding 一年实践后的冷思考

英文文化适配版: One Year of Vibe Coding: A Cold Hard Look (English cultural adaptation) 前言 最近一年我在 Google/Anthropic/OpenAI 三家烧了超过 1 万美金的 token 账单。所以本文内容基于 opus4.6、codex-5.3-xhigh、gemini3-pro 等最强模型不限量使用所表现出来的编码能力进行评价。 ...

2026-02-06 · 16 min · ming yang