Tag: ai-tools
All the articles with the tag "ai-tools".
- Updated:
AI Micro-Notes 2026: Thoughts Too Short to Trash
Short AI hot takes from 2026 onwards, accumulated from Threads and IG. Model roasts, dev pitfalls, industry observations, tool impressions — each no more than three lines.
- Updated:
AI Micro-Notes 2026: Chronological Archive
The more scattered, time-sensitive AI micro-notes from 2026, in chronological order. Curated notes (by theme) live on the main page.
-
Gemini Is Underrated Because Its Default Harness Sucks: My $140 Big Three Setup
A lot of people complain that Gemini isn't good, but Google's clunky web UI and native terminal harness are what drag it down. Once you hook it up to a proper interface via API, it easily outclasses other models in writing and multimodal work. Here is how I divide the workload across a $140-a-month Big Three setup.
-
GPT-6.1 Terra Hands-on: Fast and Cheap, but Glyphs and Chat Context Still Go to Sonnet
OpenAI just shipped GPT-6.1 Terra and says it matches Astra at a tenth of the price. I ran review, patching and screen tasks to see what you can hand it.
-
The Sweet Spot for AI Video: Be on Camera Yourself, Hand Editing and Transcripts to AI
Record your own narration on camera and let AI help with the visuals; Astra plus DaVinci Resolve did the most tedious 90% of a six-day vlog edit; Qwen 3 ASR is enough for transcripts.
- Updated:
The Economics of AI Usage: Quota Black Boxes, Subscription Math, and Calming Token Anxiety
A breakdown of AI subscription economics: from 50x official subsidies and five-hour versus weekly quota gaps to prompt caching, the night-market steak framework, and automated off-peak scheduling.
-
Where JEV Fits: Four Ways I Use It and Three Criteria
JEV is a new model that only does probability judgments and formatted output, fast and cheap. I swapped it into the semantic gates I used to run on luna and flash-lite, plus harness slimming, news filtering, and exam-question QA.
- Updated:
GPT-image-2 Wants Fewer Constraints — Plus a Consistency Drill
The "ugly crayon doodle" prompt that went viral overseas works because over-constraint kills GPT-image-2's creativity. Here is what I observed this week — including why routing prompts through Claude makes things worse, and why "consistency" matters more than raw image quality at work.
-
PII Guard TW: A De-identification Tool Built for Taiwan
There's no off-the-shelf de-identification tool for Taiwan's PII formats. So I built one that keeps sensitive data on your machine while you send the rest to AI.
- Updated:
No Error Doesn't Mean Success: Silent Failures, Opus Fabricating Tool Output, and the Hook That Finally Stops It
Exit 0, HTTP 200, and a model saying "done" are all unreliable success signals. Cases from my own code, CLIs, and APIs through to a model inventing commit hashes out of thin air, ending with the one thing that actually holds.
- 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.
- Updated:
A Year In, My Answer to "Terminal or Desktop App?" Has Changed Three Times
From March's Cowork token burn, to April's "still the terminal," to May's "beginners should just start with the desktop app," to August's "the CLI is the firstborn." One question, three different answers across five posts, laid out in the order I gave them.
- Updated:
Fable 5's One-Week Return: Turning the Most Expensive Model into a Skill Distillation Engine
Fable 5 came back for one week only. I did not spend it on daily busywork — I spent it on high-leverage judgment, distilled into skills that cheap models can follow.
-
Your AI Tools Are Now the Attack Vector: npm and Python Supply-Chain Backdoors, a $1000 Stolen-Key Bill, and a Scan-Before-You-Install SOP
Attackers are planting instructions in Claude Code, Cursor, and Gemini CLI configs so your own assistant runs the exfiltration script. Two supply-chain waves, one $1000 stolen-key bill, and the five minutes to spend before installing anything.
-
Running Local Models Won't Save You Money
If you're buying hardware to run local models just to save money, do the math with me first: capable rigs start at NT$100k, commercial models are priced to the bone, and privacy is the only irreplaceable edge left.
-
The Resource Paradox: From Stalling Old Laptops to the Real Baseline for Local AI
Many put up with aging laptops down to 1.8 GB of storage churning through swap, while dreaming of running local LLMs on a NT$5,000 machine. A look at the resource paradox, realistic hardware baselines for modern local models, and how to weigh usable speed against machine upgrades.
-
My Local Model Lineup on a Mac mini, Plus Three Bad Habits I'm Owning Up To
Ten days of offline models on a 48GB Mac mini M4 Pro — the picks, the task split, a terrifying swap write rate, and three bad habits I admit to.
-
Two Traps Running Claude Code on Local Ollama: Truncated Context, and A3B Buckling Under Heavy Verification
Two things I logged: cco (Claude Code driven by local Ollama) had long been giving off-topic answers, and the root cause was not a weak model but a full harness whose system prompt had ballooned to 30-50k tokens and was being silently truncated; then I put A3B on the Mac mini for two days as a night worker.
-
Running Taiwan Sports-Lottery Odds With Mobile Claude Code, Standing in the Lottery Shop: the Odds Are Garbage, You'll Lose
Walked past a lottery shop, felt like placing a sports bet, and on a whim wired up a betting-odds skill on mobile Claude Code right there. The verdict: the correct-score market carries a 191% overround, every expected value is negative, you lose.
-
Claude and Sensitive Data: Retention Windows, Enterprise Terms, and What to Check First
What to know before handling sensitive data with Claude: data retention windows, Enterprise contract protections, input minimization, coding agent controls, and alternative architectures.
-
Letting AI Write CAD From an Engineering Drawing: A Single Vision Model Can't Be Trusted to Read Topology
A hands-on lesson: let AI look at an engineering drawing and write CadQuery directly, and a single vision model will confidently get the topology wrong. Two more independent models and a 2:1 veto are what caught it.
-
The Claude Code Ecosystem: Skills, Hooks, and Agents in Practice
Claude Code has grown well past a basic terminal CLI into a system powered by skills, hooks, and agent orchestration. Here is how those pieces connect to keep daily workflows dependable.
-
Stop Dismissing Gemini — Four Use Cases Where Nothing Else Comes Close
Everyone seems to be dismissing Gemini now that Codex and Claude dominate the agent space. But Gemini has four use cases other models cannot match: Flash Lite cost efficiency, audio multimodal, video understanding, and book scanning OCR.
-
Two MCP servers for Taiwan public data—what mcp-taiwan-legal-db and Twinkle Hub are each good for
Two MCP servers wrapping Taiwan's public data sources—one focused on court judgments and statutes, the other aggregating 52,960 government open datasets plus 37 local utility tools. They turn out to be complementary; I now run both.
-
1M context isn't about holding more — it's about managing better
Claude Code's context window grew from 200k to 1M. The instinct is to put more in. That instinct is wrong. Five session management operations, four strategy rules, and the two most common ways to break your own context.
-
Practical Claude Code Setup: Slimming CLAUDE.md, Quota Control, and Automated Workflows
When CLAUDE.md swells past a thousand lines, instructions get dropped, and rate limits hit within minutes, your harness needs an overhaul. A practical guide to splitting Rules, Memory, and Hooks, delegating to Haiku subagents, caching rules, Ghostty click fixes, and an automated video pipeline.
-
hermes-CCC: Bringing All 46 Hermes Agent Capabilities into Claude Code
Someone ported the entire NousResearch Hermes Agent into 46 native Claude Code Skills. No OAuth, no external processes, just restart CC and you're ready. The core philosophy is "procedures-as-prompt" — structured markdown instruction scripts drive AI behavior without writing a single line of code.
-
Obsidian vs NotebookLM: Which One Works for Claude Agent Automation?
These two tools get compared a lot, but they solve fundamentally different problems. From a Claude Agent automation perspective, the difference is even clearer — one is a local knowledge base your Agent reads and writes directly, the other's API stops at "managing the Notebook itself."
-
This Week in Claude Code: Four Practical Resources I Bookmarked
From enterprise workflows and local job portals to sports analytics and beginner onboarding, four new Claude Code resources popped up this week. Each highlights a use case that hasn't been tapped enough.
-
cc-audit: A Skill That Stops Claude Code from Burning Your Tokens
I turned my viral token-saving tips into an automated audit skill for Claude Code. Feed it to Claude Code, and it inspects your settings, recent sessions, rules, and context usage to hand you an actionable checklist of fixes.
-
Make a Claude Code Tutorial Video in 30 Minutes with Remotion Skill
I'd had the Remotion skill installed for a while, mostly just playing with it. Once I started making a free Claude Code tutorial series, I realized how good it actually is—from script discussion to export, 30 minutes gets you a 15-minute video with no retakes.
-
When Your Primary AI Could Fail at Any Moment: Multi-Endpoint Fallbacks and Setup Sync for Non-Coders
When your daily work relies heavily on a single AI provider, downtime or sudden quota cuts can halt operations overnight. Here is how I evaluate fallback models for non-coding tasks, sync rules and memory across tools, and stay ready to switch.
-
Mirror System: Weekly Reviews Without the Comfort
Normal weekly reviews let you make excuses for yourself. Mirror System doesn't offer reassurance — just feed your daily notes to Claude and watch it surface the patterns you've been avoiding.
-
Turning Books into Claude Skills: From Textbooks to Atomic Habits, the World Is Already On It
Turning books, frameworks, and methodologies into Claude Skills — making knowledge executable as interactive coaches. A roundup of popular examples and practical lessons.
-
Obsidian + Claude Code: My Daily Knowledge Management Workflow
Put your entire life into Obsidian, then let Claude Code tap in. How I do daily logs, manage to-dos, and why local Markdown beats Notion.
-
claude-work-timer: Auto-Track Your Claude Code Working Hours
Billing clients by the hour with Claude Code? I built an open-source plugin to track actual working time automatically.
-
My AI Workflow: Convergence and Divergence
Distilling my AI collaboration philosophy into two modes -- convergence and divergence. Plus how I build a personal knowledge base, and my day-to-day practice of running multiple agents in parallel.
-
FIRE Planning with Claude Skills: Talking Retirement with AI
I fed all my assets, liabilities, income, and expenses into Claude Code, then just asked "am I going broke?" A month of conversations turned into a full FIRE planning toolkit — and why I open-sourced it.
- Updated:
AI Micro-Notes 2025: Thoughts Too Short to Trash
Short AI hot takes from the second half of 2025, accumulated from Threads and IG. Model roasts, dev pitfalls, industry observations, tool impressions — each no more than three lines.