Tag: codex
All the articles with the tag "codex".
-
Codex Built Its Own Evidence Package and Went to Argue With Google Support
A leaked Gemini backend key at PDT Learning got abused, no spending cap, and burned 1000 USD. I pointed Codex's browser automation at Google's live support to fight the charge, and it went so hard it built a 15-page evidence package and sent it over.
-
Codex 自己做了一份證據包，跑去跟 Google 真人客服吵架
PDT Learning 一支 Gemini backend key 外洩被盜刷、沒設 spending cap 怒噴 1000 USD，我用 Codex 的瀏覽器操作去跟 Google 真人客服爭費用，它認真到自己生出一份 15 頁證據包發給對方。
-
A Few Days Into Switching From Claude Code to Codex: The Quota Honeymoon
A running log of switching from Claude Code to Codex this week: quota I could not burn through fast enough, a $20 Sol Ultra run that beat a $100 Fable plan on a professor friend's paper, and a tool-chain swap to Hyperframe.
-
從 Claude Code 換到 Codex 的這幾天：額度蜜月期
這週從 Claude Code 換到 Codex 的體感記錄：額度多到花不完、Sol Ultra 20 鎂幫教授跑論文，比 Fable 100 鎂方案還划算，工具鏈也跟著換成 Hyperframe。
-
I Finally Switched My Daily Driver from Claude Code to Codex
I try new tools easily, but I am slow to leave the ones already built into my routine. This time, quotas, pricing, and product direction all crossed the line together.
-
我終於把主力從 Claude Code 換成 Codex 了
我很愛試新工具，卻很難離開已經用習慣的工具。這次真正讓我換主力的，不是一次 benchmark，而是額度、價格與可預見的產品方向一起越過了臨界點。
-
Which AI Is Strongest? I'll Take Them All: Claude as the Brain, Directing Gemini and Codex
Stop being a believer in one model being the strongest. Use multi-model collaboration: let Claude be the commanding brain and hand the right task to the right tool.
-
哪個 AI 最強？我全都要：讓 Claude 當大腦，指揮 Gemini 與 Codex
不要當「某家模型最強」的信徒，改用多模型協作：讓 Claude 當大腦指揮官，把對的任務交給對的工具。
-
2026 Model Personality Watch: Gemini, Claude, Codex Compared
A year in, the three flagships have developed very visible "personalities" — Gemini 3 is the dramatic PhD, Claude 4.7 is the slick veteran, and GPT-5.5 turns out to be the most pragmatic colleague of the wave. Plus a fun trick for guessing the version from "sass density."
-
2026 模型脾氣觀察：Gemini、Claude、Codex 的個性對比
用了一整年下來，三家的旗艦模型各自有很明顯的「脾氣」——Gemini 3 像戲精博士、Claude 4.7 像油條前輩、GPT-5.5 反而是這波最務實的同事。把累積的觀察整理成一篇對比，順便講一個從「貧嘴密度」反推版本號的玩法。
-
Moving from Claude Code to Codex: I Built a Skill to Handle It
Migrating an entire personal harness from Claude Code to Codex is not trivial — claude.md / agents.md, MCP, hooks, settings each need their own translation. I packaged the workflow as a Skill on GitHub. Plus a note on why I keep reaching for Codex these days.
-
從 Claude Code 搬家到 Codex：我做了一個 Skill 自動處理
把整套個人 harness 從 Claude Code 遷移到 Codex 不容易——claude.md / agents.md、MCP、hooks、settings 各自要對齊。我把流程包成一個 Skill 放在 GitHub，順便聊聊為什麼最近越來越常用 Codex。