You are here:Home»KB»Programming»My Claude AI Notes
Monday, 01 June 2026 09:24

My Claude AI Notes

Written by

my claude aI stuff

 

TL;DR

  • Claude is stateless = Everytime you respond, the whole conversation is sent and re-read so your token usage gets exponentially more on every response.
  • Use /compact to reduce your conversation size
  • /context will show your current conversation token usage.
  • use claude.md
  • Plan Mode is very useful
  • **need to chase this** Jobs that dont need an immediate response can run at a 50% discounted token rate , useful for conversions.

 

  • Commands
    • /context
      • This will show you your token usage
    • /compact
      • This will reduce your contect size by summarising the content. You can give natural language instructions to help with the process so key information does not get lost.
  • General AI Tutorials
    • How AI agents & Claude skills work (Clearly Explained) - YouTube | Greg Isenberg - I sit down with Ras Mic to break down how AI agents actually work and why most people are using them wrong. Ras Mic explains the mechanics of context windows, makes the case that agent md files are largely unnecessary, and shares his step-by-step methodology for building custom skills that make agents dramatically more productive. Whether you're coding with Claude Code or automating workflows with OpenClaw, this episode gives you the foundational knowledge to stop wasting tokens and start getting real results from your AI tools.
    • 18 Months of AI Coding Lessons in 18 Minutes (10 Tips) - YouTube | GritI Studio
      • AI coding tips that actually work. After 18 months of daily AI coding with Cursor, Claude Code, and other tools, I have distilled everything I learned into 10 tips you can learn in 15 minutes. These are battle-tested workflows I use every single day—no hype, just what actually works.
      • The models we use today are probably the worst models you will use for the rest of your life. In the past year alone, we have gone from AI that could barely autocomplete a function to agents that write entire features, create branches, and open pull requests while you drink your coffee. Hate it or embrace it—AI-assisted coding done the right way is a superpower!
  • Using Claude
  • Tutorials
    • I Took All 7 Anthropic Courses in One Weekend (Honest Review) - YouTube | Jas Wong - I spent one weekend taking all 7 of Anthropic Academy's core practitioner courses so you don't have to. In this video, I give you my honest review of each course + the exact order to take them based on who you are: brand new to Claude, a developer building with the API, or a security practitioner evaluating AI risk
    • Claude Code - Full Tutorial for Beginners - YouTube | Tech With Tim - This video will teach you Claude Code. I'll go over everything and assume no prior knowledge. I'll walk you through the setup and installation. I'll show you how to utilize the tool, the best practices, multiple features, and by the end of the video, you'll be comfortable using this tool to generate some pretty insane outputs and awesome coding projects.
  • Claude's response exceeded the 32000 output token maximum.
  • CLAUDE.md and AGENTS.md
    • CLAUDE.md and Agents.md Explained: Stop Repeating Yourself to AI - YouTube | GritAI Studio
      • CLAUDE.md and agents.md give your AI tools persistent project context so they write code that actually matches your standards from the first prompt.
      • In this practical deep dive, you will learn how AI-first teams use context files to compound results over time. Based on GitHub’s analysis of 2,500+ repositories, this video breaks down what belongs in CLAUDE.md, how to design specialist agents, and how to evolve your rules through real usage instead of upfront theory.
      • Stop Writing Bad CLAUDE.md Files - YouTube | camelCase - Most CLAUDE.md files are too long, too vague, or contain counterproductive content. Here's how to write project instructions that keep #ClaudeCode performing at its best. Backed by real #LLM research (applies to #AGENTS.md, #Cursor, #Codex too).
  • Usage Limits
  • Plan Mode

 

Read 5 times Last modified on Tuesday, 02 June 2026 14:20
Published in Programming
back to top