Tag: ai-workflow
All the articles with the tag "ai-workflow".
-
A Weekly Checklist Run by AI Only Ever Grows, So I Added a Subtraction Step
When one person or a small team has an AI run routine work from a checklist, the list only grows. Why that happens, and the monthly subtraction review I added.
-
讓 AI 跑的每週清單只會變長，我替它加了一道減法
一個人或小團隊讓 AI 照清單跑例行工作，清單只會越加越長。這篇寫清單為什麼會變長，以及我怎麼替它加每月一次的減法檢視。
-
Turning Years of Teaching into a Knowledge Base AI Can Look Up: Catching AI's Fake Quotes with Code, and Settling My Own Contradictions
I gave AI over two hundred transcripts of recorded student interviews and had it build a teaching knowledge base it looks up when preparing lessons. The AI said every quote was exact; a small program found 6 of 44 did not match. This post covers how I caught the errors, how I settle it when my own advice contradicts itself, and a starter prompt you can paste straight to an AI.
-
把十幾年的教學整理成 AI 查得到的知識庫：用程式抓 AI 的假引用，講法打架由我拍板
我把兩百多份學生面談的錄音逐字稿交給 AI，整理成一份它備課時會查的教學知識庫。AI 說引用的原話全對，一支小程式卻查出 44 筆裡有 6 筆對不上。這篇講我怎麼抓錯、我自己前後講法矛盾時怎麼拍板，最後附一段可以直接貼給 AI 的起手提示詞。
-
Turning Lesson Transcripts into a Teaching Spec: One AI Drafts, Another Finds Faults, I Only Decide
My one-on-one lessons ran 51% over schedule. I went back to the lesson transcripts, had one AI write up my teaching rules and another hunt for faults, and only made decisions on a single checklist myself. The method, the numbers, what I actually told the AI, and a prompt you can paste.
-
從課堂逐字稿整理出教學規格：一個 AI 起草、另一個 AI 挑錯，我只負責拍板
我的一對一課實際超時 51%。我回頭讀逐字稿找原因，讓一個 AI 寫上課規則、另一個 AI 挑錯，我只在清單上做決定。附做法、數字、我對 AI 說的原話與可貼用的提示詞。
-
I Built an Exam From My Own Chat Logs and Retake It With Every New Model
I turned the work I hand to AI every day into a private exam, then used it over three weeks on Claude at different effort levels, Gemini, Codex and open models. How the questions are made, how each round runs, how scores become routing rules, and prompts you can copy.
-
How a Teacher Gives Spoken Instructions to AI: Notes From 30 Classes and 751 Commands
I went through 30 transcripts of one-on-one and company classes plus 751 commands I typed to AI in my own work, to see how I actually open a request, steer midway and close it. Includes 8 original lines and a starter prompt you can paste to an AI.
-
用自己的對話紀錄出一份考卷，每次新模型出來就重考一次
我把平常交代給 AI 的工作做成一份私人考卷，三週內拿它考了 Claude 不同檔位、Gemini、Codex 和開源模型。這篇講題目怎麼出、每次怎麼考、分數怎麼變成派工規則，以及可以照抄的提示詞。
-
老師怎麼用口語對 AI 下指令：30 場課堂與 751 則指令的整理
我整理了 30 場一對一與企業課逐字稿，加上 751 則我自己工作時打給 AI 的指令，看我實際怎麼對 AI 開口、中途怎麼接話、最後怎麼收。附 8 則原話與可貼給 AI 的起手提示詞。
- Updated:
Letting Claude Dig Through a Month of My AI Chats: Habits, Mods, and Auto Mode Rules
I had Claude Code read 300-plus of my conversations from the past month. It surfaced four habits worth copying, turned three of my catchphrases into switchable auto/out/wrap modes, and the same logs can rewrite your auto mode rules.
- Updated:
讓 Claude 翻我自己一個月的 AI 對話：挖出的習慣、Mod 和自動模式規則
請 Claude Code 讀我過去一個月三百多場對話紀錄，挖出四個值得照抄的習慣、三句口頭禪做成可切換的 auto／out／wrap 模式，也能拿來改寫 auto mode 的規則。
-
Switching Your AI's Working Mode with One Command: Building work-mode and a Week of Testing
I built work-mode, a Claude Code plugin with autonomous, delegate and wrap-up modes plus desktop/phone reply formats. The pain points, how it evolved, numbers from 136 sessions, and prompts you can copy.
-
用一個指令切換 AI 的工作模式：work-mode 開發與一週實測
我做了 work-mode 外掛，讓 Claude Code 切換自主、外派、收斂三種模式，並依電腦或手機調整回覆。這篇講痛點、開發過程、136 場對話的實測數字，以及可以照抄的提示詞。
-
Measuring Again Three Months Later: From AI Adoption L2.5 to L3
In July I rated myself L2.5 on Boris's AI adoption table. Three months later I measured again: Claude can reach my knowledge base and old chats, code goes through Codex review first, schedules run everything, and 430 sessions in two weeks were started by code.
-
三個月後重量一次：我從 AI 導入 L2.5 站上 L3
七月照 Boris 的 AI 導入分級表自評 L2.5，三個月後重新量一次：知識庫和舊對話 Claude 自己拿得到、程式先過 Codex 審查、排程全面上線，兩週 430 場 Claude 是程式叫起來的。
-
Burning Quota and Saving Quota: How I Inventoried, Allocated, and Spent My AI Credits in Two Weeks
I found seven separate AI quota pools. I burned the ones about to expire on work that can check itself, and spent the surplus on things that will save quota later. Includes the inventory, my allocation rules, results, and prompts you can copy.
-
燒額度跟省額度：我這兩週怎麼盤點、分配、用掉 AI 額度
我盤點出七個 AI 額度池，一邊把快作廢的額度燒在能自己驗對錯的工作上，一邊用多出來的額度做以後能省額度的事。附盤點表、分配判準、實際成效，跟可以直接照抄的提示詞。
-
I Had a Second AI Blind-Solve My Entire Question Bank
My question bank is AI-generated, so I did not let the same AI check it. A second AI re-solved every sampled question without seeing the answer key, and people judged whatever did not match.
-
我讓另一個 AI 把自家題庫盲解了一遍
題庫是 AI 生成的，我不讓它自己檢查，而是請另一個 AI 在不看答案的情況下重做每一題，再把對不上和兩可的題交給人判斷。
-
I Asked My AI "Now What?" 41 Times in Two Weeks
Letting an AI run long jobs in the background is easy. Knowing where it got to when you come back is not. I counted two weeks of my own messages and found I was missing a status board, not more monitoring.
-
我兩週問了 AI 41 次「現在呢」
讓 AI 在背景跑長任務很簡單，難的是回來時一眼看懂它跑到哪。翻完自己兩週 1,053 則訊息，我發現缺的不是監控，是一張自己能看的狀態表。
-
Don't Refill the Seat, Let Claude Cover It
I ran AI training at a friend's company near Zhongshan Station. Four people left in an office of a dozen computers, workflows turned into skills and routines, and the business still runs fine.
-
遇缺不補，人少了就 Claude 來頂
去中山站附近一間朋友開的公司做 AI 培訓，四個人守著十幾台電腦的辦公室，工作流固定成 SKILL 和 routine，遇缺不補，業務一樣做得好好的。
-
Read the System Card Before You Use a New Model
I read the personality assessment in every new model's system card before deciding how to work with it. Opus 5.5 is a gentle senior advisor with opinions, Sonnet 5.5 is a hands-on builder, and Haiku 5.5 just goes into the dispatch rules.
-
用新模型之前，先讀系統卡：Opus、Sonnet、Haiku 5.5 的個性與對應方式
每次新模型發布我都會讀系統卡裡的個性評估，再決定怎麼跟它互動。Opus 5.5 是溫和有主見的幕僚，Sonnet 5.5 是愛幹活的實作派，Haiku 5.5 則寫進派工規則就好。
-
How I use herdr: three workspaces for standing, today and long-term
After Opus 5.5 analyzed 30 days of my session logs, I split herdr into standing, today and long-term workspaces. Four status lights keep the standing agent aware, and Opus can jump into the next pane to rescue a task.
-
我怎麼用 herdr：常駐、今日、長期三個工作區
請 Opus 5.5 分析 30 天 session log 後，我把 herdr 工作區分成常駐、今日、長期；四種燈號讓常駐 agent 掌握全場，還能叫 Opus 跳到隔壁窗格救場。
-
Can Haiku 5.5 Take Over Sonnet's Work? I Tested It on My Own Tasks
Instead of official benchmarks, I built a test from 761 sub-agent jobs I actually delegated over 45 days. On seven checking tasks Haiku 5.5 matched Sonnet and Opus at about a tenth of the cost; long transcript extraction is still not complete enough.
-
Haiku 5.5 能接 Sonnet 的活嗎？我拿自己的工作考它
不看官方跑分，從自己 45 天、761 次的 subagent 派工裡挖題目考 Haiku 5.5。查核類七題它跟 Sonnet、Opus 同分，成本約十分之一；長逐字稿抽取還是不夠完整。
-
Why GPT 6 Sol / Luna Feel So Dumb
A small job, transcribing consulting videos: the smart model builds a pipeline, the dumb one does every step by hand. After Opus 5.5 took over Codex's mess, it found four failure modes in 6 Sol / Luna, and why Cost per Task now needs a time variable.
-
為什麼 GPT 6 Sol / Luna 用起來這麼蠢
一個轉錄諮詢影片的小任務，聰明模型先搭管線、笨模型步步親力親為。請 Opus 5.5 接手 Codex 的爛攤子後，分析出 6 Sol / Luna 的四個失敗模式，以及 Cost per Task 該多一個時間變數。
-
Opus Commands, Sonnet Implements, Fable Advises: How I Split the Work Across Three Models
With Opus 5.5, Sonnet 5.5 and Fable 5.1 all out, my split is: Opus leads, verifies and deploys, Sonnet implements as a subagent, and Fable gets called in now and then as an advisor.
-
Opus 指揮、Sonnet 實作、Fable 當顧問：三個模型的分工
Opus 5.5、Sonnet 5.5、Fable 5.1 都有了之後，我自己的分工是 Opus 親自指揮驗證部署、Sonnet 當 subagent 實作、Fable 偶爾請出場當顧問。
- Updated:
Do Not Grade AI by Its Own Summary
I hit the same failure in several forms this week: an agent denied changing files, a commit message overstated the diff, and a transcript reassigned a speaker ID halfway through. A later batch added checks that never ran and still reported clean.
-
After Using Opus 5.5, Many of My Old Skills Need a Rewrite
With no Skill and no open-source project, Opus 5.5 one-shotted a fully animated video, then translated and subtitled a Vietnamese stand-up special. Weekly quota barely moved, and the Skill details I wrote to rein in older models all need a second look.
- Updated:
不要用 AI 的摘要驗收 AI
這週反覆踩到同一類錯誤：agent 說沒改檔卻留下檔案、commit message 與 diff 不符、逐字稿說話人中途漂移；一個多月後又補上檢查器沒在檢查卻回報正常的一整批。驗收必須回到原始狀態。
-
用了 Opus 5.5 之後，過去寫的 Skill 都要重新調整
不給 Skill、不給開源專案，Opus 5.5 one-shot 剪出整支動畫影片，又把越南語單口喜劇翻譯壓字幕。週額度幾乎沒動，過去為了規範模型寫的 Skill 細節都該重新審視。
- Updated:
Most of the Gains From AI Adoption Have Little to Do With AI
From hands-on work, most of what an organization gains from adopting AI comes from fixing permissions, data governance, buy-in and redundant processes along the way, not from the AI itself.
-
Getting AI to Write Like Me: From LoRA Fine-Tuning to a Three-Gate Skill
LoRA fine-tuning Qwen3 8B nailed my writing style but produced incoherent content, so I switched to a Claude skill with punctuation, sentence-level, and ending gates instead, and got results about as good as fine-tuning.
-
Running 5+ Claude Code/Codex at Once: My Five Fixes for the Attention Bottleneck
Once I have more than 5 Claude Code/Codex windows going, I hit an attention bottleneck — constant context switching is genuinely exhausting. Five things that get me past it: a good multi-window manager, voice input, an overnight schedule, a reviewable skill, and regular pruning.
-
Before and After Coaching: Grill-me Prep, 80/20 Coach, Fable 5.1 Todos
Before a career coaching session I used Opus 5.5 with the Grill-me SKILL to build a prep sheet, then the coach ran 80/20 to surface blind spots, and Fable 5.1 turned my notes into todos afterward.
- Updated:
Letting an Agent Tune a Local Video Model Overnight: My Three Gates
Three things I learned from letting an agent run local video-model parameter research overnight: hard constraints in CLAUDE.md, a gate script watching SSD writes, and a 30-minute check-in loop.
- Updated:
When to Call In Fable: Three Moments, and Don't Turn On ultracode
The most expensive model is not meant to run the whole way. Three moments where calling in Fable feels right to me, plus why I cap Opus 5 at med, and the weekly cycle I fell into: efficiency king Monday to Thursday, Fable mode Friday to Sunday.
- Updated:
大部分 AI 導入的效益，其實跟 AI 沒什麼關係
從實作經驗看，組織導入 AI 得到的效益，很多來自權限、資料治理、遊說與冗餘流程被順手處理掉，而不是 AI 本身。
-
讓 AI 寫得像我：從 LoRA 微調到 SKILL 三道閘門
拿 LoRA 微調 Qwen3 8B 學自己的文風，文風像但內容支離破碎；改寫成 SKILL 讓 Claude 寫、加上標點／逐句／結尾三道閘門，效果跟微調差不多。
-
同時開 5 個以上 Claude Code／Codex，我的五個注意力瓶頸解法
同時開超過 5 個 Claude Code／Codex 視窗時會遇到注意力瓶頸，一直 context switching 真的很累。分享目前跳脫這個瓶頸的五個做法：多窗口管理器、語音輸入、夜間排程、reviewable skill、定期做減法。
-
職涯諮詢前後：Grill-me 準備、教練 80/20、Fable 5.1 收待辦
職涯諮詢前用 Opus 5.5 配 Grill-me SKILL 整理小抄，諮詢中教練 80/20 引導點醒盲區，會後把筆記交給 Fable 5.1 整理待辦。
- Updated:
讓 Agent 整夜自己調本地影片模型：我設的三道閘門
讓 agent 夜間自己跑本地影片模型調參的三個經驗：硬約束寫進 CLAUDE.md、閘門腳本監控 SSD 寫入、30 分鐘回來盯一次避免快取失效。
- Updated:
何時派工 Fable？三個時機，還有別開 ultracode
最貴的模型不是拿來全程跑的。三個我體感最好的 Fable 派工時機、為什麼 Opus 5 我最多開到 med，以及我後來變成週一到週四效率王、週五到週日 Fable 模式的那個循環。
-
Astra Scouts, Luna Max Finishes: Crawling Niche Sites With Heavy Anti-Scraping
A crawl method for sites with thorough anti-scraping that are too niche for any third-party scraping company to cover: Astra scouts and writes the SKILL, then Luna Max runs the batches.
- Updated:
Why Obsidian is something special to me, and why I only made this video now
I'd been wanting to make this video for a long time, but kept putting it off. Obsidian's flexibility is so high that it grows into a different shape in every person's hands. The payoff isn't immediate either—it's only after the vault has grown for a while that you realize you can't go back.
-
Astra 探路、Luna Max 收工：反爬太徹底又太小眾的網站怎麼爬
反爬做得很徹底、又小眾到沒有第三方爬蟲公司 cover 的網站，先派 Astra 探路寫成 SKILL，再交給 Luna Max 自動批次跑的爬蟲心法。
- Updated:
Obsidian 為什麼是個特別的存在——我為什麼到現在才拍這部影片
這部影片我想做很久了，但是卻一直沒做，直到今天。Obsidian 的自由度太高，所以在每個人的手上會長成不同的樣子。他的成效又不是立刻就能看到的，而是越長越大你才會發現離不開它。
-
Why Client Conversations Drift
Notes from a client diagnosis: three root causes, four prescriptions, plus the main/sub agent pairing run backwards and the rambling only a hook can cure.
-
客戶的對話為什麼會飄掉
一次客戶診斷的隨筆：三條病狀根因、四條解方，外加主副 agent 反過來搭的模型組合，以及只有 hook 治得了的話癆。
- Updated:
My Client's Chat Blew Up: Three Questions in One Prompt, and Claude Just Drifted Along With Him
Asking about revenue, metrics, and decisions in a single prompt, or never persisting conclusions after brainstorming. Two real-world cases of client drift with AI, and the fieldwork of using /explain, /first-principles, Grill-me, and checkpoint to rein their workflows back in.
- Updated:
More Subagents Won't Make You Faster
From wanting 13 subagents to chat for me, to one person running 1000, to agents arguing across a table — the real bottleneck is the human main agent, and the fix is deduping before you dispatch.
- Updated:
客戶的對話爆掉了：一段 prompt 塞了三件事，Claude 就陪著他一起發散
一段 prompt 裡同時問業績、問指標、問決策，或是聊完從不落檔。兩個客戶與 AI 協作時的發散現場，以及我用 /explain、/first-principles、Grill-me 與 checkpoint 把工作流收斂回來的實戰。
- Updated:
派更多 subagent 不會讓你更快
從想派 13 個 subagent 代聊、一個人操控 1000 個，到面對面互審代碼的荒謬幻想——真正的瓶頸是人類這個 main agent，解法是先去重去衝突再派工。
- Updated:
AI Tool Philosophy — Pick a Mindset, Not a Side
After making nearly thirty tutorial videos: tools change, thinking doesn't. Don't dismiss others' tool choices. What matters is the orchestration logic — task decomposition, validation planning, responsibility assignment.
-
Hand the Dharma to Your Agent and Let It Discipline Itself
A SKILL called buddhist-method that constrains agent behavior with six Buddhist concepts: verify before asserting, look for root causes, re-check actual state, throw the draft away, cut the cause instead of hiding it, and don't change position under pressure.
- Updated:
7 Practical Tips for Talking to Claude 5: Less Drift, Less Chatter, Less Slacking, Less Nagging
Some practical tips I have been sharing with friends lately on talking to the Claude 5 generation of models: a home-made explain skill for alien-speak, answering everything in one pass instead of letting the conversation drift, voice-input setups, first-principles pruning, a hook that treats slacking, a minimal CLAUDE.md, and a fix for the phantom pushback habit.
- Updated:
Two Worlds of Web-Based Claude Code Setup
Web Claude Code has two completely different runtimes — cloud VM and remote-control. Here is what I learned setting up both, the small bugs I hit, and why some user-level configs simply cannot be lifted to the cloud as-is.
- Updated:
The More Rules You Add, the Less Claude Listens — I Sent a Team of Agents to Trim My Setup and Cut 36% of Always-On Context
Late at night I got Opus 4.8, and my weekly quota happened to reset. The first thing I did was put my harness on a diet. A COO student who had burned through 88% of his 1M context made me face one thing squarely: the more rules you add, the less the model listens.
-
Just Swap the Outer Loop
LongHorizon-Harness wraps around agents like Claude Code and Codex. It does not train the model or replace your agent, it only runs the loop, and WeaveBench completion went from 51.8 to 80.7.
- Updated:
AI 工具使用哲學——不選陣營，選思維
拍了快三十部教學影片後的感觸：工具會變，思維不變。不用否定別人的工具選擇，真正重要的是指揮的邏輯——拆分任務、規劃驗證、分配職責。
-
把佛法交給 agent，讓他用佛法約束自己
一個叫 buddhist-method 的 SKILL，用六條佛法概念約束 agent 的行為——查證、找根因、重新確認狀態、丟掉草稿、捨斷成因、不因壓力改立場。
- Updated:
跟 Claude 5 對話的 7 個實用技巧：不發散、不話癆、不偷懶、不雞婆
一些最近跟朋友分享的，跟 Claude 5 代系列模型對話的實用小技巧：自製 explain skill 抓外星話、一次回完別讓對話發散、語音輸入配置、first-principles 剪枝、用 hook 治偷懶、CLAUDE.md 極簡化，以及治雞婆的幻影反駁。
- Updated:
網頁版 Claude Code 環境設定的兩個世界
網頁版 Claude Code 有兩種環境——雲端 VM 跟 Remote-control。這篇整理我實測下來的設定訣竅、會踩到的小 bug，以及為什麼有些設定不能無腦丟到雲端。
- Updated:
規則越加，Claude 越不聽話——派一隊 AI 重整設定，常態上下文省 36%
半夜拿到 Opus 4.8、額度剛好重置，我做的第一件事是減肥我的 harness。一個 COO 學員把 1M 上下文用到 88% 的案例，讓我認真面對一件事：規則加越多，模型反而越不聽話。
-
只換外面那圈 loop
LongHorizon-Harness 架在 Claude Code、Codex 這些 agent 外面，不訓練模型也不取代你的 agent，只做迴圈，WeaveBench 完成率從 51.8 拉到 80.7。
-
ABC Legal's Agent Fleet: Turning AI Experiments Into a Governed Production System
Six cards summarizing Anthropic's ABC Legal case study: 50+ production agents, agents managed as software in git, a steering committee with no software developers on it, and the principle that trust comes before automation.
-
Once It Ships, It's Gone: Three Times an Agent Misfired on an External System
Calendar invites, replies, and the internal notes on a hold event are all one-way doors. I got each of them wrong once this month, so here are the shapes of the accidents and the checks that catch them.
-
A Chatty Model: Teaching Opus 5 to Converge
Opus 5 does not speak plainly, and it also overwrites. A cue card turns into a treatise. I use a first-principles skill to teach it to converge.
-
Five Things I Never Saw Coming Two Years Ago
Five changes in myself I never saw coming two years ago: the terminal, cancelling Office 365, voice input, dispatching AI agents, and a desktop that finally got cleaned up.
-
ABC Legal 的代理人艦隊：把 AI 實驗變成可治理的生產系統
整理 Anthropic 官方 ABC Legal 案例的六張圖卡：50+ 生產環境代理人、把 agent 當軟體放進 git、非工程師組成的 steering committee，以及「可信任，才自動化」的營運原則。
-
寄出去就收不回來：agent 動外部系統的三次誤操作
行事曆邀請、回信、佔位事件的內部備註，這三種動作都是寄出即無法收回。這個月我在這三處各犯一次，記下事故形狀與防呆判準。
-
話癆的模型：教 Opus 5 怎麼收斂
Opus 5 除了不講人話之外還會過度寫作，小抄寫成萬言書。我用 first-principles skill 教它收斂，順帶談怎麼遏制 overthinking。
-
兩年前從來沒想過會發生在自己身上的五件事
兩年前從來沒有想過、卻真的發生在自己身上的五個變化：終端機、退訂 Office 365、語音輸入、派 AI Agent，還有被整理乾淨的桌面。
-
My Context Window Is More Fragile Than Today's Frontier Models: I Open-Sourced a Document Review SKILL
Working with an agent drains my attention, so I worked out a review loop: he writes the full proposal, I review it by voice, he revises, I go eat and exercise, then v2 shows up.
-
我的 Context Window 比當今大模型還脆弱：我開源了一個文檔審查 SKILL
跟 Agent 合作會注意力耗弱，於是我摸索出一套審查流程：請他出完整提案書，我錄音審查，他改，我去吃飯運動，等 v2。
-
The Alignment Gap Is Closing. Next Comes Taste and Verification
The gap between AI and human intent is closing fast, so what separates good output moves toward taste and verification — and verification is where human responsibility stays.
-
Other People Fly to Korea for Cosmetic Surgery. I Had Codex Do Mine.
Someone on Twitter chained Codex, Hyperframes, IndexTTS2 and HeyGen into a one-person media pipeline. I pulled the repo, tried it, played with a local TTS model, then rebuilt a video days later on Claude Code.
-
Fewer Prompts Is Not Less Control
Claude 5 and GPT-5.6 official guidance is converging on the same thing — retiring old-style prompt stacking. But trimming is not letting go; control just moves. And the payoff of maintaining that layering is switching tools without losing a step.
-
Porting Old Prompts to Opus 5: A Nine-Card Migration Guide
Nine cards I made after reading Anthropic's official Opus 5 prompting guide: response length, agent narration, task boundaries, subagent delegation, self-correction, and what happens when you turn thinking off.
-
Two Habits for Voice-Driving Coding Agents, and I Am Still Finding the Balance
Short instructions go through push-to-talk; walking through a whole course outline or system architecture goes through a full QuickTime recording that I hand to the AI to transcribe and execute. Plus the setup I use to burn the AI quota that came free with Google Drive.
-
對齊的 gap 正在縮小，接下來拚的是品味與驗證
AI 對齊人類意圖的 gap 正在快速縮小，區分產出品質的要素會往品味與驗證轉移；而驗證背後是人類永遠不會被取代的責任。
-
別人去韓國做醫美，我叫 Codex 數位醫美
從推特上看到有人把 Codex、Hyperframes、IndexTTS2、HeyGen 串成一條自媒體流水線，拉下來實測、順手玩 b 站的本地 TTS，幾天後換 Claude Code 重做一支。
-
更少的 prompt，不是更少的控制
Claude 5 與 GPT-5.6 的官方指南正在合流，都在淘汰舊式 prompt 堆疊。但精簡不等於放任，控制只是換了位置——而維護好這套分層的紅利，是換哪個工具都能立刻接手。
-
舊 prompt 搬到 Opus 5：九張卡的遷移指南
讀完 Anthropic 官方的 Opus 5 提示指南後整理的九張卡：回答長度、代理敘述、任務邊界、子代理委派、自我修正，還有關掉 thinking 的副作用。
-
語音下指令的兩種習慣，我還在找平衡
用 Claude Code 或 Codex 時，短指令我用隨按即錄，要盤點整套思路時我改開 QuickTime 完整錄音，再丟給 AI 轉錄執行。附上我拿 Google 雲端硬碟送的額度做轉錄的設定。
-
I'm Stuck at Stage 2.5 of AI Adoption
After watching Boris Cherny break down the stages of AI adoption, it hit home: I'm stuck at stage 2.5, where limited attention plus low trust becomes a vicious cycle. This week I used late-night schedules, a morning dashboard, and herdr auto-spawning sessions to cut a 4-5 hour workflow down to 1-2 hours.
-
我卡在 AI 導入的 2.5 階段
看了 Boris Cherny 分享的 AI 導入階段框架後有感而發：我卡在 2.5 階段，注意力有限加信任不足變成惡性循環，這週靠深夜排程、晨間儀表板、herdr 自動開 session 把 4-5 小時的協作壓到 1-2 小時。
-
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。
-
Picking a Brand Look as a Non-Designer: AI Made Prototypes Cheap, So Taste Became the Hard Part
I am not a designer, but I spent this week iterating on a visual system for AgentCrew Academy with Fable, GPT-image-2, and GPT-5.6-sol. Here are the four rejected directions and the final spec applied to the website, slides, and documents.
-
外行人選品牌視覺：AI 把提案做便宜了，難的變成你的品味
我不是設計師，這週用 Fable、GPT-image-2、GPT-5.6-sol 迭代出 AgentCrew Academy 的視覺系統，記下被否決的四個方向與最後套用到網站、投影片、文件的規格。
-
"Automation" Isn't the Answer to Most Things — and How I Made This Video
Why do the people teaching AI keep bringing up "automation"? I don't think automation is the answer to everything, or even to most things. Plus a few words on how I made Ep27.
-
Claude Code To-Do Tiering: Auto / Review / Collaborate / Manual
A small discovery from using Claude Code: sort to-dos by repo, then into four tiers — auto, review, collaborate, manual. Stuff that used to drag on all day now finishes in an hour.