Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

-OpenAI has completely overhauled its model naming system with the release of GPT-5.6, introducing three distinct tiers: Sol, Terra, and Luna. In this video, we put OpenAI's new flagship model, GPT-5.6 Sol, to the ultimate test. Using the Codex extension in VS Code, we throw our classic "Build me a secure notes app or I get fired" prompt at Sol. Watch as we break down the pricing and reasoning differences of the new tiers, run a full security audit using Snyk, and see if Sol's $5/$30 price tag is truly production-ready or if a small local CSRF bug gets us "fired" first.

In this video, we break down why skipping code reviews is a massive mistake that will ultimately slow you down, leave you vulnerable, and compromise your system's accountability. We dive into three concrete reasons why reviewing AI-generated pull requests actually makes you a faster, safer developer, including a real-world story of a production bug caught in under 90 seconds. Resources Chapters.

GLM 5.2 just launched from Z.ai, and it might be one of the biggest threats yet to the frontier model premium. It’s open, significantly cheaper than Claude Opus 4.8, and claims to deliver near-frontier coding performance across major benchmarks. But benchmarks only matter if the model can actually build something production-ready.

In this video, we break down how to properly set up and use AI extension points - specifically MCP (Model Context Protocol) servers, Rules, Skills, and Hooks - to supercharge your development workflow. Using practical, security-flavored examples with Claude Code and Snyk, you'll learn how to configure a local project environment that automatically catches vulnerabilities before they ever hit your codebase. Whether you use the Claude CLI, VS Code extensions, or alternate AI ecosystems like Cursor or Gemini, you can use these exact steps as a blueprint to automate any workflow in your project.

Over 78% of developers are using Claude for coding, but almost everyone is leaving its single most powerful feature switched off: Claude Skills. In this video, we break down what Claude Skills are, how they use "progressive disclosure" to keep your context window light, and the 7 best engineering skills you can install this week to completely supercharge your workflow.

We put Anthropic’s new Claude Opus 4.8 to the test using our standard benchmark: building a secure, production-ready Notes app. Anthropic claims this model is four times less likely to let security flaws slip through. Operating on "Ultra Code" mode, the AI navigates environment blocks, writes its own E2E security test suite, and runs dependency audits. We walkthrough the final app and run a security scan using the Snyk CLI to see if Claude's code is truly safe to deploy.

235,000 installs per week. That’s how quickly developers are downloading AI agent skills — packages that give AI coding agents new capabilities like shell access, file system operations, cloud access, and deployment permissions. But unlike traditional npm packages, agent skills introduce a completely new security problem: natural language instructions that AI agents can interpret and execute autonomously.

On May 11, 2026, the TanStack namespace was hit by a "Mini Shai-Hulud" supply chain attack. Unlike typical attacks, this did not involve stolen credentials; instead, the threat group TeamPCP hijacked the legitimate GitHub Actions release pipeline. This video covers the technical details of the OIDC token extraction, the "Dead Man's Switch" that triggers a rm -rf / upon credential revocation, and the mandatory remediation order you must follow to save your data. We also discuss how to harden your workflow using release-age cooldowns and OIDC pinning.

Are you confused by the terminology surrounding AI coding tools? You aren't alone. In this video, we break down the four essential components that transform a basic LLM into a powerful coding agent: Rules, Skills, Hooks, and the Model Context Protocol (MCP).

GPT-5.5 vs Claude Opus 4.7 - two flagship AI models dropped one week apart, and both claim to be the best at agentic coding. We put that to the test by giving each model the exact same prompt: build a production-ready, secure note-taking application from scratch. But we didn't stop at reviewing the code. We actually tried to break it by running real security tests against each app to see whether AI-generated code can be trusted with user data. The results were not what we expected.