AI News Today | Julian Goldie Podcast

AI Agents Gone Rogue: The True Story of a Dev Under AttackThis is the chilling true story of Scott Shambal, a developer who was targeted by an autonomous AI agent after rejecting its code. We break down the five technical components that turn a helpful tool into a persistent entity and explain how to build safe AI guardrails.00:00 - Intro: The AI Hit Piece01:03 - The Rejection That Started It All0...

Myrrofish: The AI Prediction Tool Built by a 20-Year-Old Discover Myrrofish, the open-source tool that uses thousands of AI agents to simulate real-world human behavior and market reactions. Learn how to leverage this prediction machine to test your pricing, content, and business strategies with digital replicas of your audience. 00:00 - Intro: The $4.1M Student Project 00:30 - How Myrrofish Simul...

Pi Coding Agent: The 16x Cheaper Alternative to OpenClawDiscover why the Pi coding agent is disrupting the AI space by offering a leaner, faster, and significantly cheaper foundation for building agents. Learn how to take full control of your automation workflows while cutting token costs by up to 16 times compared to pre-built platforms.00:00 - Intro: The New AI Agent Killer?00:38 - Pi vs. OpenCl...

Start a One-Person AI Business with Claude: 30-Day RoadmapLearn how to bridge the gap between business needs and AI automation by starting your own one-person agency in just 30 days. This guide covers everything from content creation and sales calls to building recurring retainer offers using Claude AI. 00:00 - The AI Automation Opportunity 00:41 - Step 1: Content & Building Authority 02:46 -...

Make Claude Code 100x Better with Karpathy's Secret RulesLearn how to transform Claude Code into a world-class developer using principles from AI expert Andrej Karpathy. By installing a simple set of four rules, you can prevent AI from overcomplicating projects and making bad assumptions. This free method has been shown to reduce coding errors significantly and ensure cleaner, more surgical result...

7 Best AI GitHub Repos You Must Try Today (Open Source)Discover the most powerful trending AI GitHub repositories that are changing the way we code and automate tasks. From self-improving agents like Hermes to Karpathy's coding principles, learn how to install and leverage these free open-source tools today. 00:00 - Intro: Best AI GitHub Repos 01:06 - Hermes Agent: The Self-Learning AI 04:18 - Kar...

Obsidian + AI Agents: Make Your Notes 10x More PowerfulLearn how to integrate AI agents directly into Obsidian using the Agent Client Protocol and Claude Code. This setup allows you to automate note-taking, improve your knowledge base, and create a two-way interaction between your AI and your personal data. 00:00 - Intro: AI Agents in Obsidian 01:10 - Installing the BRAT Plugin 01:43 - Setting up...

5 Massive Google AI Updates: Gemma 4, Veo 3.1 & New Features Google just released five major AI updates in a single week, including the powerful open-source Gemma 4 and the cost-saving Veo 3.1 Light. This video breaks down how these tools can lower your operational costs and streamline your content creation workflow through smarter pricing and precise editing features. 00:00 - Intro: 5 New Goo...

How to Run GLM 5.1 for Free: The Best Claude Alternative! Learn how to set up and run GLM 5.1, the powerful flagship AI model from Zhipu AI, for free using tools like Claude Code and OpenClaw. Discover how to bypass expensive token costs with this fast, smart, and highly capable alternative to traditional LLM providers. 00:00 - Intro: Why Switch to GLM 5.1? 01:02 - How to Download and Install 01:5...

Claude's New App Builder Leaked: The End of No-Code Startups? Anthropic accidentally revealed a revolutionary full-stack app builder integrated directly into Claude. Discover how this new interface, alongside the secret 'Conway' agent, is set to disrupt the software development landscape and replace existing no-code tools. 00:00 - Intro: The Claude App Builder Leak 00:17 - Leak Analysis: Interface...

How to Run GLM 5.1 for Free: The Best Claude Alternative! Learn how to set up and run GLM 5.1, the powerful flagship AI model from Zhipu AI, for free using tools like Claude Code and OpenClaw. Discover how to bypass expensive token costs with this fast, smart, and highly capable alternative to traditional LLM providers. 00:00 - Intro: Why Switch to GLM 5.1? 01:02 - How to Download and Install 01:5...

Anthropic Just Killed 1,000 AI Startups: The Agent Revolution Anthropic’s release of Claude Managed Agents has overnight made the complex AI middleware layer obsolete. Discover how this shift from technical infrastructure to operational thinking allows you to automate your business workflows in minutes rather than months. 00:00 - Intro: The AI Startup Wipeout 01:08 - How Anthropic Replaced Middlew...

This Free AI Model Trained ITSELF: Minimax M2.7 Full Breakdown Discover Minimax M2.7, the groundbreaking open-source model that improved its own performance by 30% through autonomous self-training. Learn how this free tool rivals GPT-4 and Claude Opus in real-world coding, finance, and multi-agent workflows. 00:00 - The AI Model That Trained Itself 01:30 - M2.7 vs GPT-4 & Claude Benchmarks 02:...

This Free AI Model Trained ITSELF: Minimax M2.7 Full BreakdownDiscover Minimax M2.7, the groundbreaking open-source model that improved its own performance by 30% through autonomous self-training. Learn how this free tool rivals GPT-4 and Claude Opus in real-world coding, finance, and multi-agent workflows. 00:00 - The AI Model That Trained Itself 01:30 - M2.7 vs GPT-4 & Claude Benchmarks 02:4...

Google Jitro: Why Prompting Is Dead (New AI Agent) Google’s new AI agent, Jitro, is shifting the paradigm from manual prompting to goal-driven execution. Discover how this KPI-led approach will redefine coding, agency workflows, and the future of AI collaboration. 00:00 - The End of Prompting 01:03 - Goal-Driven AI vs. Task-Based AI 02:32 - What Makes Jitro Different from Jules? 03:20 - KPI-Driven...

Meta Muse Spark: The New AI Model Changing Business Forever Meta has invested $14.3 billion into Muse Spark, a multi-agent AI model that is already disrupting the industry. Discover how its ecosystem integration and superior health benchmarks can give your business a massive competitive advantage. 00:00 - Intro: Meta’s $14.3B AI Bet 01:08 - How Muse Spark Uses Multi-Agents 02:29 - Benchmarking Mus...

GLM 5.1: The New 8-Hour Autonomous AI Agent Changing Coding China's Z AI just released GLM 5.1, a massive open-source model that ranks top three globally for coding and can work autonomously for 8 hours straight. Discover how its 'long horizon' capabilities allow it to self-correct and outperform giants like GPT-4o and Gemini. 00:00 - Intro: GLM 5.1 Changes AI Agents 01:18 - Long Horizon Task Capa...

Perplexity AI's Huge Finance Update: Manage Money with AI Perplexity AI has integrated with Plaid, allowing you to link your financial accounts and manage your money using simple AI prompts. This update transforms the search engine into a personal financial hub that builds custom dashboards, tracks budgets, and forecasts cash flow automatically. 00:00 - Intro: Perplexity x Plaid 00:38 - The End of...

Claude Code + Obsidian: Build a Stateful AI Knowledge Base Stop using AI like a search engine and start building a stateful knowledge base that grows smarter over time. This workflow uses Claude Code and Obsidian to turn raw information into a permanent business asset inspired by Andrej Karpathy. 00:00 - Intro: The Karpathy Workflow 01:04 - The 3-Folder Architecture 02:02 - Claude Code as a Compil...

Hermes AI Agent: Why Everyone is Switching from OpenClaw Hermes has become the fastest-growing AI agent of all time by introducing a revolutionary closed-loop learning system that builds its own skills. Discover how this autonomous tool outperforms the competition with native memory, cross-platform gateways, and the ability to manage complex business workflows. 00:00 - Intro 00:35 - Who is Nous Re...

Anthropic Just Changed AI Agents: The Claude Advisor Tool Anthropic's new Advisor Tool gives your AI agents Opus-level intelligence at a fraction of the cost by allowing cheaper models to consult a senior strategist only when needed. Discover how this update makes complex business automations more reliable and cost-effective than ever before. 00:00 - Intro: A New Era for AI Agents 00:34 - How the...

Claude Code Monitor: The End of Polling and Birth of Background AI Anthropic just released the Monitor tool for Claude Code, shifting AI from costly polling to efficient event-driven background execution. Discover how this update saves tokens and enables fully automated, always-on agents that respond to real-world events in real time. 00:00 - Intro: Claude Code's New Monitor Tool 00:12 - The Probl...

Google Gemini's New Notebooks: Your AI Second Brain Is HereGoogle just integrated NotebookLM features directly into Gemini, transforming it from a simple chatbot into a powerful project management tool. Discover how to upload 100+ sources and organize your work into dedicated notebooks to supercharge your business productivity. 00:00 - Intro: Gemini's Game-Changing Update 00:41 - What are Gemini N...

GLM 5.1: The First Open-Source AI That Works for 8 Hours StraightGLM 5.1 is a massive breakthrough in open-source AI, capable of working autonomously for up to eight hours to solve complex tasks without human intervention. Discover how this model outperforms GPT-4 and Claude in benchmarks and learn how to leverage its long-horizon capabilities for your business. ⁠00:00⁠ - Intro: A New AI Shift ⁠00...

Hermes Agent 0.8: The Massive Update You Need to SeeHermes 0.8 brings over 200 updates including background notifications, live model switching, and native Google Gemini support. This release significantly improves AI agent reliability and introduces advanced remote code execution capabilities.00:00 - Intro: Hermes 0.8 Overview00:15 - Background Notifications & Live Switching01:32 - GPT Reliab...