Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

In this video, I’ll be putting Google’s Gemini 2.5 AI to the test — challenging it to generate 100% secure and safe code for a note taking application. The catch? My job is on the line... and the code has to pass all security checks to avoid critical vulnerabilities. I’ll be diving into how Gemini 2.5 performs under pressure and examining whether AI can truly be trusted with secure coding. Resources.

AI Coding Mistake...

ChatGPT 4.1 Generates Outdated Code...

In this video, I put OpenAI's latest model, ChatGPT-4.1, to the test to see if it can generate secure code. Can AI really help us write safer, bug-free applications? Or does it still fall into common security pitfalls like SQL injection, XSS, and insecure auth flows? Stay tuned to find out!

Claude AI Reads and UNDERSTANDS an Image...

In this video, I challenge Claude AI to a head-to-head match in the board game King of Tokyo Duel. I walk the AI through the rules, give it everything it needs to understand how to play, and then we battle it out! Claude picks up the game shockingly fast — its strategy, decision-making, and logic were next-level. I was seriously mind-blown at how intelligent it was… Should we put this to the test with other AI's like ChatGPT?

How to EASILY Check for Vulnerabilities with Snyk.

Aider is SUPER Powerful BUT...

How to get Set Up with Aider!

The Features of Aider.