Tag: ai-tools
All the articles with the tag "ai-tools".
-
AI Micro-Notes 2026: Thoughts Too Short to Trash
-
Claude Seeing Ghosts Four Nights Straight: A Log of Opus 4.8 Fabricating Tool Output
-
AI 碎念日記 2026：那些太短但捨不得丟的觀點
-
Claude 半夜見鬼連續四天：Opus 4.8 捏造工具輸出實錄
-
Opus 4.8 Cries 'Prompt Injection,' Codex GPT-5.5 Tracks Down the Real Cause: a Worktree Race
-
Opus 4.8 搞烏龍報『提示注入攻擊』，Codex GPT-5.5 揪出 worktree race 真因
-
Running Taiwan Sports-Lottery Odds With Mobile Claude Code, Standing in the Lottery Shop: the Odds Are Garbage, You'll Lose
-
在彩券行用手機 Claude Code 算運彩賠率：台運賠率爛透了，誰下誰賠
-
Which AI Is Strongest? I'll Take Them All: Claude as the Brain, Directing Gemini and Codex
-
哪個 AI 最強？我全都要：讓 Claude 當大腦，指揮 Gemini 與 Codex
-
No Error Doesn't Mean Success: Five Silent Failure Traps in AI Dev
-
沒拋錯不代表成功：AI 開發裡的五個靜默失敗陷阱
-
Two Mindsets for Getting Unstuck: Logical Thinking, and the AI Pedagogy of Never Making the Same Mistake Twice
-
卡關時的兩個心態：用邏輯思考，與『不貳過』的 AI 教育學
-
Teaching a Talent Agency to Use Claude Code, and the Soft Landing of the DK Confidence Curve
-
帶藝人經紀公司用 Claude Code，與 DK 信心曲線的軟著陸
-
The Five-Step SOP for Sneaking Claude Code Runs From the Hotel Over Dinner
-
出門吃飯前，讓 Claude Code 在旅館背景偷跑的五步 SOP
-
From Miasma to Hades: How One Group Turned AI Tools Into a Supply-Chain Attack Vector
-
從 Miasma 到 Hades：同一個攻擊組織如何把 AI 工具當成供應鏈攻擊媒介
-
Testing Fable's Limits on a Professor Friend's Paper Repo
-
拿教授朋友的論文 repo 試 Fable 的能力邊界
-
A Few Takeaways from the Claude Code Anniversary Talk
-
Don't Dump the Last Session's JSON — Check Your Harness First
-
Claude Code 週年對話的幾個重點
-
別把上一個對話的 JSON 餵給它，先體檢 harness
-
What to Know Before Handling Sensitive Data with Claude
-
用 Claude 處理敏感資料前必知
-
"Automation" Isn't the Answer to Most Things — and How I Made This Video
-
A Few Months With Claude Code: The Companion Tools and Resources I've Accumulated
-
The Teleprompter That Saved My English-Only Teaching, and the Open-Source AI Meeting Copilot I'm Evaluating
-
Model Picks Beyond the Main One: Notes I Left at Different Times
-
Letting AI Write CAD From an Engineering Drawing: A Single Vision Model Can't Be Trusted to Read Topology
-
The Day Opus 4.8 Went Haywire: tool call cannot be parsed
-
「自動化」不是大部分事情的解方——以及我怎麼拍這部影片
-
用 Claude Code 這幾個月，累積下來的周邊工具與學習資源
-
全英文授課的提詞器救星，以及我正在評估的開源 AI Meeting Copilot「Natively」
-
主力之外，各模型的定位：我在不同時間留下的選型碎念
-
讓 AI 看工程圖寫 CAD：單一視覺模型裸寫拓樸不可信
-
Opus 4.8 全線抽風的一天：tool call cannot be parsed
-
Don't Brute-Force Sites That Need a Login—Your Token Is Your Account
-
需要登入的網站別硬爬——你的 token 就是你的帳號
-
AI Tool Philosophy — Pick a Mindset, Not a Side
-
AI 工具使用哲學——不選陣營，選思維
-
Claude Code Ecosystem Overview — Skills, Hooks, Agents in Full Bloom
-
Claude Code 生態系盤點——Skill、Hook、Agent 全面開花
-
Stop Dismissing Gemini — Four Use Cases Where Nothing Else Comes Close
-
別一味貶低 Gemini——四個其他家打不過的 Use Case
-
Two MCP servers for Taiwan public data—what mcp-taiwan-legal-db and Twinkle Hub are each good for
-
台灣公開資料兩個 MCP 評測——mcp-taiwan-legal-db 跟 Twinkle Hub 各適合什麼場景
-
GPT-image-2 Wants Fewer Constraints — Plus a Consistency Drill
-
GPT-image-2 越少約束越好，加上一個一致性練習
-
AI community digest W18: Claude detects Codex cheating, GPT 5.5 guardrails confuse everyone
-
AI 社群週報 W18：Claude 偵測到你在偷用 Codex、GPT 5.5 的過濾器到底鬆了沒
-
1M context isn't about holding more — it's about managing better
-
1M Context 不是裝更多，而是管理更好：Claude Code Session Management 心法
-
Claude Code this week: 1M context as a management problem, quota anxiety goes collective, SpaceX takes Cursor
-
Claude Code 這週整理：1M Context 怎麼用、額度焦慮集體發作、Cursor 被 SpaceX 搶走
-
Claude Code This Week: Offloading CLAUDE.md, Quota-Saving Tricks, Ghostty Click Fix
-
Claude Code 這週整理：分擔 CLAUDE.md 的進階設定、省 quota 技巧、Ghostty 點擊設定
-
Claude Code Subscription Guide: The Real Gap Between Pro and Max
-
Why Claude Code Only Reaches Its Full Potential in the Terminal
-
Claude Code 訂閱怎麼選：從 Pro 到 Max 的真實落差
-
為什麼 Claude Code 在終端機裡才是完全體
-
Claude Desktop App Got a Redesign — Here's Why I'm Still Using the Terminal
-
hermes-CCC: Bringing All 46 Hermes Agent Capabilities into Claude Code
-
Obsidian vs NotebookLM: Which One Works for Claude Agent Automation?
-
Claude Desktop App 改版了——以及我為什麼還是用終端機
-
hermes-CCC：把 Hermes Agent 的 46 個能力全部裝進 Claude Code
-
Obsidian vs NotebookLM：用 Claude Agent 自動化知識管理，選哪個？
-
This Week in the Claude Code Ecosystem: Four Resources I Bookmarked
-
本週 Claude Code 生態觀察：四個我收藏的新資源
-
cc-audit: A Skill That Forces You to Save Claude Code Quota
-
cc-audit：一個強迫你省 Claude Code 額度的 Skill
-
Make a Claude Code Tutorial Video in 30 Minutes with Remotion Skill
-
用 Remotion Skill 半小時拍一支 Claude Code 教學影片
-
Is Claude Getting Dumber? Someone Finally Brought Data
-
Claude 變笨了？這次有人拿出數據證據
-
PII Guard TW: A De-identification Tool Built for Taiwan
-
PII Guard TW：為台灣打造的個資去識別化工具
-
Anthropic's Trust Crisis and My Backup Plan
-
Anthropic 信任危機與我的備援方案
-
Mirror System: Weekly Reviews Without the Comfort
-
Mirror System：用 Claude 做不帶安慰的週回顧
-
Why Does Cowork Hit Your Limit in Hours While Claude Code Runs All Day?
-
為什麼 Cowork 幾小時就頂到限額，Claude Code 整天都沒事？
-
Turning Books into Claude Skills: From Textbooks to Atomic Habits, the World Is Already On It
-
把書變成 Claude Skill：從教材到原子習慣，國外已經在瘋了
-
Obsidian + Claude Code: My Daily Knowledge Management Workflow
-
Obsidian + Claude Code：我的日常知識管理工作流
-
One AI Tool to Rule Them All: Why I Only Recommend Claude Code
-
一個 AI 工具打天下：為什麼我只推薦 Claude Code
-
AI Security Boundaries: The Lobster Craze, Presidio, and My Three Rules
-
AI 的安全邊界：龍蝦熱潮、Presidio、與我的三條鐵則
-
claude-work-timer: Auto-Track Your Claude Code Working Hours
-
claude-work-timer：讓 Claude Code 自動算工時
-
My AI Workflow: Convergence and Divergence
-
我的 AI 工作流：收斂與發散
-
FIRE Planning with Claude Skills: Talking Retirement with AI
-
用 Claude Skill 做 FIRE 理財規劃：跟 AI 聊退休