Claude Clue #19: Stop Babysitting Claude with AutoMode
Let Claude decide what's safe and what isn't...!
Christopher Moravec
Episode 62 - Break The AI
I built an 8-bit video game-style AI red teaming game that lets you try to break various chatbots with different guardrails so you can see how it works.
Claude Clue #18: Compact, Clear, or Resume: Know Your Options
Claude Code now gives you real tools to manage your conversations, and knowing when to use each one matters.
Episode 61 - Ask Jaws
I built a chatbot for my website using the five-layer guardrail stack from Episode 58. My AI agent wrote the code, then a separate AI agent attacked it. You can try to break it too.
Claude Clue #17: Don't Wait! Keep Moving While Claude Works
Patience is a virtue when working with AI, but sometimes you don't actually have to wait.
Episode 60 - Say Hello, Jaws
I built an autonomous AI agent that runs 24/7 on a Mac Mini, manages my home office, triages my email, helps write content, and improves itself every night at 3 AM. Here's an introduction to how it actually works.
Claude Clue #16: Stop Staring and Let Claude Ding You
Small automations that fire at specific points in Claude's lifecycle. A simple example: playing a sound!
Episode 59 - Poison Pills
Poison pills are hidden instructions in data your AI consumes. They’re a fun defensive trick for content creators and a serious attack vector if you’re building AI tools that touch external data.
Claude Clue #15: Skills Are Just Files Your Model Can Find
A skill is essentially a file that your model can access on demand to tailor its behavior for a specific task.
Episode 58 - Guardrails
It takes more than a good system prompt to protect an AI from abuse, and it is worth making it as hard as possible for attackers.