What Chinese AI video generators cost, and whether you can pay from Singapore
You can sign up for most Chinese AI video generators with just an email, and none of their open-weight licences excludes...
Guides & How-tos · Worked examples · Real numbers
Do it right, with real numbers
Step-by-step how-tos, head-to-head comparisons and honest roundups — every guide worked through with current figures, then backed by a RECATOOLS calculator or AI-directory entry so you can act on it.
510 guides published
17 topic areas
Latest guide Oct 2026
Statistics
35
Health & Wellness
33
Cybersecurity
30
Business
19
Privacy & Data
17
Consumer Tech
14
ASEAN Tech
13
Personality
9
Cloud & Infra
8
Cyber Threat Intel
7
Sustainability
5
Advertisement
Do DeepSeek and Qwen need different prompts from ChatGPT
"Avoid adding a system prompt" is the most-repeated rule about prompting Chinese models, and DeepSeek's own current docu...
How many tokens is a Chinese character, and what Chinese AI companies call things
Four Chinese model vendors publish the same ratio in their own documentation: a Chinese character is about 0.6 of a toke...
Advertisement
One embedding model, four different maximum lengths
The most downloaded sentence-embedding model ships four config files declaring 128, 256, 512 and 512 as its maximum inpu...
One token can double your bill
OpenAI charges 2x input and 1.5x output on the full request once a prompt passes 272,000 tokens, so the 272,001st token...
Two providers charge a toll for your prompt cache. One charges rent.
All three major providers price a cache read at a tenth of normal input, so caching looks like the same deal everywhere....
Your AI Coding Agent Charges You for Coffee Breaks
A long session is cheap. An interrupted one is not. Every AI coding agent re-reads your whole conversation at a tenth of...
How to Stop ChatGPT, Claude, Gemini and Grok Training on Your Chats (2026)
Four switches with almost the same name, doing four different things. Three are on by default. One also sets your retent...
How to Measure Whether Your RAG Is Retrieving the Right Documents
Twenty questions with known answers, run over 205 real documents. Prefixing titles to chunks raised hit@1 from 14 to 17...
How to Give an Agent Search Over Your Own Documents
Seventy-eight lines with no dependencies join a local embedding model, a vector store and MCP. The interesting part is n...
How to Generate Embeddings Locally
A 46 MB model, running on your laptop, turns text into positions in space. The demonstration: a query whose only content...
How to Self-Host Qdrant in Docker
Every retrieval tutorial says "point it at your vector database" and none of them tells you how to run one. One containe...
Advertisement