Models differ in size, in the data they learned from, in what they were further trained for, in window size, speed and price.

In depth: 00 · ABC: six words before you start → “4. Why there are so many models, and how they differ”

Related: token · model gateway

Appears in

• 00 · Kickstart: Your ghost idea · Map of tools
• 03 · Stack selection: What are your constraints? · Matrix of 4 stacks · Behind a censorship firewall: no VPN · Hermes + local stack · Migration plan for your workflow
• 04 · Prompt Engineering: My worst prompt · Magic words · The sins of prompting · A professional prompt
• 06 · Automation Pipeline: The info you process by hand · Build your pipeline · A pipeline that runs on its own
• 07 · Tools & Extensions: MCP: superpowers through a protocol
• 08 · Agent Engineering: Jagged Intelligence: What to Delegate · Orchestration: Gmail Agent as a Case · Prototype → Production · Agent SDK: the Agent as a Library
• 09 · AI Notebook: How it works
• 10 · Model Training: What's inside a model · Data is the main work · Fine-tuning: when and how · Evaluation: did it help · Practice: fine-tune a small model
• 11 · Second Brain: A second brain that stays with you · Skills travel from agent to agent · Security: everything that comes from outside · Practice: build your own second brain

The course is free — start on the site →

Write to the author: Telegram · LinkedIn

checked against the course: 2026-11-02 · 664b147