harryf

A walkthrough of the 2025 OWASP Top 10 for Large Language Model applications, the most common security threats teams hit when they put LLMs into production, plus the defenses for each.

• Video: Explained: The OWASP Top 10 for Large Language Model Applications (IBM Technology, ~25 min)
• OWASP guide: OWASP Top 10 for LLM Applications | 2025 list (genai.owasp.org)

Each section links to its timestamp in the video and to the matching entry in the official OWASP 2025 guide. Rank movements are versus the 2023 list.

---

Intro - why this matters

harryf

PAI: Getting started

PAI (Personal AI Infrastructure) is an open-source layer on top of Claude Code that adds structured thinking, persistent memory, specialized skills, security guardrails, and voice feedback. Think of it as Claude Code on steroids: same CLI, same model, but with a system around it that makes every interaction more capable.

Created by Daniel Miessler. Free and open source.

Install

macOS or Linux. Takes about 2 minutes.

harryf

PAI: Getting started

PAI (Personal AI Infrastructure) is an open-source layer on top of Claude Code that adds structured thinking, persistent memory, specialized skills, security guardrails, and voice feedback. Think of it as Claude Code on steroids: same CLI, same model, but with a system around it that makes every interaction more capable.

Created by Daniel Miessler. Free and open source.

Install

macOS or Linux. Takes about 2 minutes.

harryf

The Dark Code Crisis: AI-Generated Software Nobody Can Explain - And How to Fix It

Source: This is a summary of a YouTube video Nate B Jones (ex-Amazon). Watch the original video

Overview

As AI tools generate ever more production code at speed, a new class of problem has emerged: "dark code" - code that works, passes tests, and ships, but that no human on the team ever truly understood. This video argues that dark code is not primarily a security or tooling problem, but an organizational capability problem, and lays out a three-layer framework for fighting it before it becomes a liability.

---

harryf

How AI Agents & Claude Skills Work (Clearly Explained)

Source: This is a summary of a podcast/YouTube video featuring Ross Mike discussing AI agents, context windows, and skill-building strategies. Watch the original video

---

Overview

Ross Mike joins a podcast to share his hands-on philosophy for getting the most out of AI agents like Claude Code and OpenCloud. The core message: the models are already excellent — what separates great results from mediocre ones is how you structure context and build skills, not how many tools you stack on top. He argues against bloated agent.md files and downloaded skill packs, and instead advocates for iteratively teaching your agent your specific workflows from scratch.

harryf

Nicholas Carlini - Black-hat LLMs | [un]prompted 2026

Source: This is a summary of a talk by Nicholas Carlini (Anthropic researcher) at the [un]prompted 2026 security conference. Watch the original video

---

Overview

Nicholas Carlini presents alarming evidence that modern LLMs can autonomously find and exploit zero-day vulnerabilities in critical software — including the Linux kernel and production web applications — with minimal scaffolding. He argues this represents a phase shift in the attacker/defender balance comparable in magnitude to the invention of the internet, and urges the security community to treat this as an urgent, present-day threat rather than a future concern.

harryf

Karpathy's "autoresearch" Broke the Internet

Source: This is a summary of a YouTube video by Greg (solo commentary format). Watch the original video

---

Overview

Andrej Karpathy released an open-source project called autoresearch — an AI agent that autonomously runs iterative experiments overnight (code edits, training runs, metric evaluation) and keeps only the improvements. The video explains what it is, explores 10 business use cases, and covers how to get started without an NVIDIA GPU.

harryf

How to Switch Between Work and Personal Anthropic Accounts with Claude Code and Claude Desktop

A guide for running two Anthropic accounts (e.g., work Team/Enterprise + personal Pro/Max) on the same macOS machine, with one-command switching for both Claude Code (CLI) and Claude Desktop.

Platform: macOS (uses macOS Keychain; Linux would need adaptation) Claude Code Version: 2.x Claude Desktop: Electron-based (1.x+)

---

harryf

How I Use Obsidian + Claude Code to Run My Life

Source: This is a summary of a YouTube video featuring Greg Eisenberg and his guest Vin (Internet Vin). Watch the original video

Overview

Greg and Vin walk through how pairing Obsidian (a plain-text note-taking app) with Claude Code (an AI agent) creates something more powerful than either tool alone — a personal thinking system that notices patterns in your life, helps you reflect, and turns your notes into real actions. The conversation moves from setup basics all the way to live demos of AI reading someone's personal vault and generating surprisingly personal, useful ideas.

---

harryf

Lecture 7: Agentic Coding

Source: This is a summary of a MIT Missing Semester lecture on agentic coding. Watch the original video

Overview

This lecture covers coding agents — AI models wrapped in an "agent harness" that can autonomously read/write files and execute shell commands to complete programming tasks end-to-end. The lecturer demonstrates Claude Code live, explains how LLMs and agent harnesses work under the hood, walks through key use cases, and covers advanced features like parallel agents, context management, and sub-agents.

---