THE PERSONAL NOTEBOOK OF WARLOCK TOME
A little curiosity.
A little magic.
From World of Warcraft addons to small ideas brought to life. A place to collect the things I make, one page at a time.

THE COLLECTION
Made along the way
2026
- Why there's no warning before the breakthrough: the 59.27% tipping point
A ~6-minute math animation (Chinese narration) with a full write-up. Some say effort below the tipping point means nothing. I fill a 1,000-square sheet of graph paper at random and pour water in from the top: at square 592, all 25 rows light up at once. Then I simulate many sheets to find the 59.27% cliff and check how much of the saying holds.
- OpenAI Decisions API vs Jev: 20 tests, 10,000 calls
An ~18-minute hands-on video (English narration) with a full write-up. I gave Jev and OpenAI's new Decisions API the same 20 tests, 10,000 calls in total: Jev won 8, Decisions won 1, and 11 were ties. The article goes through the 5 groups, then speed, price and confidence, and ends with which one to pick for which job.
- Ballpoint · Beat-Synced Drawing
Upload a photo and get it drawn stroke by stroke in ballpoint, synced to a BPM, as a video.
- JT8-3 · Ballpoint Edition
Arknights JT8-3 redrawn in ballpoint pen: deploy operators and fight the Black Snake in your browser.
- Galewing
A 3D grapple-and-slash game: swing across the rooftops and shatter stone golems’ cores from behind.
- Opus 5.5 Built a Math Game Kids Get Hooked On, in 40 Minutes
A ~5-minute video (Chinese narration) with a full write-up. I started from a tweet video and gave the AI (Opus 5.5) just one sentence. The first version was ready in 13 minutes. In under 40 minutes, the kids' math game 「嗨算!」 was live on my homepage. This article explains how it was made and how the AI caught its own mistakes. It also asks whether over-the-top practice games are actually good for kids.
- Jev as a RAG judge: top-1 hits from 7 to 17
A ~7-minute hands-on video (Chinese narration) with a full write-up. Where in a RAG pipeline should Jev go? I built a small RAG on TypeSafe's official docs and tested it with 36 hand-written English questions: after re-ranking, top-1 hits went from 7 to 17, every near-miss and unrelated question was blocked, and I also spell out what it can't do.
- 嗨算!
An arithmetic drill that escalates: every correct digit pumps up the score, the effects and the music. Preschool to Grade 4.
- Can open-source Laya replace Jev? 6/14 on SQL, then 3.9 hours of fine-tuning
An 11-minute hands-on test (Chinese narration). On 14 SQL review cases Jev gets 13 right; the open-source decision model Laya gets 6. After 3.9 hours of fine-tuning on an M4 Mac, Laya reaches 14/14 on safety, but still trails on correctness.
- AI News Shorts
Two 60–90 second vertical shorts on generative AI news every day (models and business). Research, script, narration and rendering all run automatically.
- Giving an AI limbs: how Jev plays Doom in real time at 120 ms
A 7-minute breakdown (Chinese narration). No pixels, no screenshots — just a plain-text state report, queried about ten times a second. Jev picks the goal like a commander; ordinary code does the key presses.
- 10,000 API calls later: reverse-engineering Jev's architecture
A 13-minute explainer (Chinese narration), based on Archer Hume's outside-in experiments with latency, token counts and option order. Jev doesn't generate token by token; it reads probabilities out, and encodes shared state only once.
- 10 ways to use Jev, after testing it on 3 of my own tasks
A 10-minute explainer (Chinese narration) with a full write-up. Task routing: 17 of 20 right. Kanban classification: 87%. Can this SQL ship: 14 of 14. Then ten ways to use it, how it splits work with an LLM, and where it falls short.
- Jev Tweet Radar
Scores every post on your X timeline with Jev: worth engaging, buzz, misread, AI-ish… and checks your own draft before you hit Post. Open-source Chrome extension.
- Understanding Jev: a System-One tool for data engineers
A 4.5-minute explainer (Chinese narration, English UI). Jev is TypeSafe's System One Model: one forward pass, no token-by-token decoding, calibrated probabilities at about 1/400 the cost of a frontier LLM.
- Auto Query Now
Reads values from URL query parameters and types them into the focused input on the page, optionally pressing Enter. Turn any form into a shareable link.
- NotebookLM Quick Capture
Save any page into NotebookLM in one click. Pick a notebook, send the URL or page text, and keep your research moving without leaving the tab.
2015
2014
- KtUF
Simple unit frames with draggable positioning, paired with tMark for status markers.
- tMark
Moving markers that convey health, mana, and energy along a custom line.
- tChat
A hotkey for switching chat channels, replying to whispers, and adjusting the chat window.
- tDD_UnitFrame2
Standalone unit frames built around portraits, resource bars, and combat state.
- tTalent
A visual treatment for the talent frame, with configurable effects and a control panel.
No entries in this category yet.






















