AI News Today | Julian Goldie Podcast

Hermes Agent Goals Mode: Run Autonomous 24/7 Tasks for Free (No More “Keep Going”)The video introduces Hermes Agent’s new free “Goals” update, which lets users set a long-horizon objective once and have the agent run autonomously until completion without repeated prompts. It demonstrates launching a goal to create and host a blog, then explains how Goals mode works via a persistent standing objective, a conservative judge model that decides after each turn whether to continue, and an adjustable default 20-turn budget with auto-pause and resume. The script contrasts this with the old workflow that required constant “keep going” prompts, context loss, and human babysitting. It covers commands like /goal status, pause, resume, and clear, notes local goal-state persistence and per-goal directories, briefly discusses preferred tools/LLMs (including Grok 4.3 and Antigravity CLI), and ends by promoting the AI Profit Boardroom for an agent OS setup, roadmap, coaching, and community.00:00 Goals Update Overview00:43 Launching Your First Goal02:11 How Goal Mode Works03:37 Old Way vs New Way05:50 Live Q&A Tooling Talk06:36 Judge Budget Loop Explained07:28 Commands Examples Persistence08:15 Free Setup Use Cases08:59 Common Objections Recap09:56 Boardroom Offer Closing11:03 Thanks For Watching

Hermes Agent Setup Guide (Free): Best Models, Hermes vs OpenClaw, Video + Blog AutomationThe video answers common questions about Hermes Agent, described as a powerful free AI agent, including how to install it on macOS via a one-line GitHub command, which model providers to use (prioritizing Groq OAuth with a Twitter subscription, ChatGPT OAuth with a subscription, or free options like Owl Alpha on OpenRouter and another free provider with Step 3.5 Flash), and whether to switch from OpenClaw. It advises not switching if OpenClaw already works, but notes Hermes is smoother and easier to control while OpenClaw updates can break things. It covers generating videos with Hermes using Hyperframes or Groq OAuth, running Hermes in the cloud via a VPS (with users using Hostinger), and creating SEO blogs and Q&A landing pages using an Agent OS setup, skills, and deployment via a Netlify access token. It also mentions a shared memory context system, Hermes controlling the Claude CLI, and using free Claude Code with Owl Alpha.00:00 Hermes Agent Overview00:27 Live Q and A Setup01:28 Install and Pick Models02:31 Cheapest Model Providers03:30 Hermes vs OpenClaw05:22 Video Generation Options06:28 Cloud Hosting Without Hardware07:30 Blogs and Landing Pages10:19 Recap and Netlify Deploy11:37 Join the Community12:19 Classroom and Memory System13:29 Claude Integration Explained

Hermes Beats OpenAI Codex, DeepMind Drops Antigravity CLI, and Musk Teases AI SatellitesThe episode covers four fast-moving AI stories relevant to building AI-driven businesses in 2026: OpenAI Codex is reportedly slowing down and losing reliability, with over 1,700 posts in 24 hours prompting public switching—mainly toward Claude Code—while early benchmarks show the self-improving Hermes Agent outperforming Codex on key speed tasks. Google DeepMind also released Antigravity CLI, a new terminal-based coding agent tool positioned as a replacement for Gemini CLI, enabling more complex agentic coding workflows from the command line with free testing under token limits. Elon Musk teased a forthcoming detailed design reveal for TerraFab, a Tesla/SpaceX/xAI project aiming to put AI compute in orbit via satellite-based data centers powered by constant solar energy and different cooling dynamics, potentially lowering AI costs industry-wide. The script advises building AI workflows in modular layers so tools can be swapped without rebuilding everything, and promotes the AI Profit Boardroom’s coaching and agent operating system.00:00 AI News Rundown00:33 Codex Slowing Down01:30 Hermes Beats Codex01:57 What It Means Business03:54 DeepMind Antigravity CLI05:21 Google Agentic Future06:02 Musk AI Satellites07:22 Cheaper Compute Impacts08:27 Switch Tools Without Rebuilds09:49 Zoom Out 2026 Rhythm10:46 Final Sign Off

Claude Mythos-1: 23,019 Vulnerabilities Found + Sonnet 4.8 Leaks (June Release?)The script covers two major Claude updates: Mythos-1 and leaked details on Sonnet 4.8. It claims Claude Mythos Preview scanned 1,000+ open-source projects in 30 days, found 23,019 vulnerabilities (6,202 high/critical) with a 90% true-positive verification rate, including large sets of issues for Cloudflare and Firefox, and it reportedly blocked a $1.5M wire-fraud attempt at a partner bank by detecting behavioral patterns without human intervention. It describes the challenge that AI can find vulnerabilities faster than humans can patch them, Anthropic’s response via Claude Security auto-patching, and an open-sourced bug-finding pipeline, plus Cisco building a similar system. It also discusses brief sightings of Mythos-1 Preview in Claude Code/Security despite public caution, Jack Clark’s Oxford remarks on AI risk, and accidental leaks indicating Sonnet/Opus 4.8 testing in Google Vertex with an expected mid-to-late June timeframe and new reasoning improvements.00:00 Mythos-1 and Sonnet Leaks00:26 Mythos Scanning Results01:05 Real World Bug Finds01:32 Bank Fraud Stopped02:13 Patch Backlog Problem02:54 Claude Security Auto Patching04:16 Mythos-1 Preview Spotted05:05 Safety Messaging Tension06:27 Sonnet 4.8 Leak Details06:55 Vertex Testing Signals07:27 Expected Sonnet 4.8 Upgrades08:11 Big Picture Takeaways09:09 Business Implications09:28 Three Common Objections10:25 How to Get Started11:15 Final Wrap Up

Why Andrej Karpathy Joining Anthropic Could Change Claude (and Your Business) in 2026The script argues that Andrej Karpathy joining Anthropic on May 19, 2026 is more than a talent move because he is joining the pre-training team to use Claude to make future versions of Claude smarter, reflecting a shift toward AI improving AI. It highlights Karpathy’s background (OpenAI founding team member, former Tesla AI lead, founder of Eureka Labs, and creator of “vibe coding”) and his recent “Auto Research” project, where an agent ran 700 experiments in two days, stacked ~20 improvements, and achieved ~11% speed gains on a benchmark. The video emphasizes “context engineering” over prompt engineering—building workflows, files, and knowledge bases (e.g., LLM Wiki) around models—and predicts a context marketplace, more goal-based command loops, and an education layer to help users build agentic systems as models rapidly improve.00:00 Karpathy Joins Anthropic00:29 Who Is Karpathy01:16 Using AI To Improve AI01:45 Auto Research Loop03:12 Context Beats Models04:40 LLM Wiki Knowledge Base05:17 Building Business Context06:16 Education And Adoption Gap07:17 Three Big Predictions09:30 Early Adopters Pull Ahead10:14 Recursive Self Improvement11:05 Why This Matters For You12:27 Karpathy Signal To Watch13:45 Final Question And Wrap

Hermes Agent OS: Build a Mission Control Dashboard to Run All Your AI Agents 24/7The episode introduces Hermes Agent OS and shows how to build a single “mission control” dashboard to run multiple AI agents together with shared memory, sessions, skills, and a Kanban workflow. The presenter demos a workspace that previews AI-generated apps, plays back created videos, manages images, text-to-speech, podcasts, and integrates tools like NotebookLM, an SEO system that can deploy content across five websites, and a knowledge base that stores persistent notes and context. Viewers are advised to ask Hermes to generate and locally host the dashboard, iterating daily rather than using the terminal, and to connect additional agents (Claude, OpenClaw, Gemini, Codex) into one system. Q&A covers e-commerce automations using Grok 4.3 and Shopify CLI, starting with one agent and one automation per week, local security precautions, Noose Portal APIs, Codex cloud access, Tailscale for VPS connections, and an Obsidian transcript-to-notes automation success story.00:00 Hermes Agent OS Launch00:19 Mission Control Vision01:32 Tour of Agent Workspace02:48 Swarms and Shared Memory03:35 Build Your Own Dashboard04:23 Why Not the Terminal04:59 Connect Other Agents and APIs06:22 Community Questions Begin07:37 Ecommerce Automation Setup10:18 Real Estate VA Strategy11:29 Grok vs ChatGPT12:20 Security and Local Control12:50 Onboarding and Noose Portal14:27 Codex Cloud and VPS Access15:51 Best Prompting Skill Workflow16:53 Automation Win With Obsidian18:08 Wrap Up and Boardroom Access19:02 Final Thanks and Goodbye

Hermes Agent’s Free Computer-Use Upgrade: Control Your Mac in the Background (Plus Phone Control)The video explains a new free Hermes Agent update that enables “computer use” so the agent can click, type, scroll, open apps, and complete tasks on a Mac in the background while you keep working, with a later promise of controlling it from a phone. The presenter demos creating formatted Notes entries, drafting automation ideas, opening recently modified apps, and organizing the desktop, then explains setup using CUA Driver by copying a URL into Hermes or running simple install commands, granting permissions, and testing. They compare Hermes to n8n as a faster, no-code, free, less technical option. The script highlights how the agent works via screenshots and background dispatching, notes guardrails that require approval for destructive actions, and discusses local vs VPS usage. It ends by promoting an “agent operating system” workspace and the AI Profit Boardroom community with guides, training, coaching calls, and networking.00:00 Free Upgrade Overview00:47 Live Demo Notes Automation02:13 Installing CUA Driver02:45 Hermes vs n8n Explained03:39 Desktop Cleanup Example04:00 How Background Control Works06:18 Goals Over Tasks Mindset06:53 Quick Install Steps07:53 Guardrails and Safety09:47 Recap Key Benefits10:16 Agent OS and Boardroom Tour12:26 Q&A Managing Agents at Scale13:43 Building a Better UI System15:14 Phone UI Options and Wrap Up

Build an Infinite Context Engine: Claude + Obsidian Second Brain (Free Setup with Omi)The video explains how to build a free “infinite context engine” by wiring Claude (or other AI agents) to an Obsidian vault so every conversation starts with full context instead of fragmented native AI memory. The creator shows a color-coded Obsidian knowledge graph that links goals, projects, people, tools, and daily work, and introduces a three-part stack: Omi (open source capture layer that listens, records, and creates notes/tasks), Obsidian (local Markdown-based storage and graph), and Claude (reader/organizer that can restructure the vault). It covers organizing the vault with Tiago Forte’s PARA (Projects, Areas, Resources, Archive), using a two-way loop where chats both read from and write back to the vault, and two ways to connect Claude to Obsidian (MCP Obsidian or a local folder), plus mentions community resources and Q&A about Hermes and multi-website SEO.00:00 Claude Second Brain Intro01:00 Obsidian Memory Graph Tour02:48 Why Claude Memory Fails04:31 Omi Capture Layer Setup06:40 Obsidian Vault Basics07:29 Claude Reads and Organizes08:33 Markdown Graph and Tags10:01 Connect Claude to Vault11:37 PARA Structure Explained12:52 Two Way Feedback Loop13:37 Objections and Recap15:39 Boardroom Resources Pitch17:02 Live Q&A Wrap Up

5 Free Hermes Agent Use Cases (Videos, Websites, Swarms, Podcasts + Agent OS)The script explains five free use cases for Hermes AI Agent to unlock more of its capabilities: generating videos with open-source skills like Hyperframes (and Remotion) including text-to-speech, using a built-in Kanban board to run a multi-agent swarm where an orchestrator triages a one-line mission into subtasks, connecting Hermes to Google’s free NotebookLM via an open-source MCP/CLI to automate podcasts, infographics, and videos from sourced material, building SEO content, apps, games, and full websites inside a workspace with previews and history (with examples of traffic growth), and tying everything together by having Hermes build an “agent operating system” dashboard that integrates tools like Obsidian memory, Kanban, studio features, journaling, and multiple agents, with an optional prebuilt setup available in the AI Profit Boardroom community.00:00 Free Hermes Agent Overview01:10 Use Case 1 Hyperframes Video Maker02:35 Free APIs With OpenRouter03:41 Use Case 2 Kanban Agent Swarm07:53 Use Case 3 NotebookLM Content Factory10:05 Use Case 4 SEO Sites Apps Games13:15 Obsidian Memory Context Boost14:04 Use Case 5 Agent Operating System16:25 Live Q&A Setup Tips19:02 Mindset Blocks And Next Steps20:37 Join The AI Profit Boardroom

Master the Hermes AI Agent OS: Setup, SEO, and Memory Secrets

Learn how to build a powerful Mission Control for your AI agents using the Hermes Operating System. This guide covers local installation, SEO content pipelines, and how to use Obsidian as a second brain for your automation stack.

00:00 - Intro to Hermes Agent OS

00:53 - Running Hermes on Your PC

02:32 - Deploying Agent OS in the Cloud

03:18 - Automated Backlink Building

05:11 - Best AI Models: Grok vs GPT

08:02 - Hermes vs Anti-gravity

08:43 - Using Obsidian for AI Memory

13:27 - Migrating ChatGPT Data to Obsidian