AI News Today | Julian Goldie Podcast

Hermes Agent Computer Use (New Update): Your Mac AI That Clicks, Types & Works in the BackgroundThe video covers a new “Computer Use” update for Hermes Agent that lets an AI operate a Mac desktop in the background—clicking, typing, scrolling, and dragging without moving your cursor or interrupting your work—using an MCP server. The host walks through updating Hermes, installing Computer Use via a CLI command, granting macOS Accessibility permissions, and notes it’s experimental with safety guardrails and approval prompts for risky actions. They demonstrate Hermes opening Apple Notes and creating a new, personalized journal note with ten time-saving ideas, then attempt a more complex Obsidian organization task that proves slower and less reliable. They also show Hermes opening Terminal to run Hermes and type “hello,” discuss model options (needs vision), token/screenshot costs, and how to switch/setup models, and direct viewers to the AI Profit Boardroom for a guide with prompts and a roadmap.00:00 Hermes Gets Superpowers01:02 What Computer Use Does01:40 Install and Update Hermes03:34 Permissions and Safety Notes04:50 How to Use It06:17 Quick Test Open Notes06:53 Auto Journal Note Demo08:37 Obsidian Second Brain Attempt10:18 Prompting Framework11:51 Models Costs and Limits13:37 Hermes Talks to Itself15:50 Results Recap and Limits16:56 Common Objections Answered17:50 Guide and Community Plug18:56 Switch Models in Hermes

OpenClaw 5.9 Pre-Release: Real-Time Discord Voice Agent, iMessage Catch-Up, WeChat + Breaking Change WarningOpenClaw 5.9 appears on GitHub as a pre-release beta, adding major updates including a revamped Discord voice experience with a new default “agent proxy” mode for real-time listening and speaking using OpenAI or ElevenLabs voice models, plus improved interruption and echo handling. It introduces iMessage catch-up so the agent processes messages received while offline, but removes the BlueBubbles method, which can break existing iMessage setups unless migrated to Apple’s direct Mac connection. The update also adds personal WeChat (Tencent Weixin) support, adds Mistral Medium 3.5, retires Gemini 3 Pro in favor of Gemini 3.1 Pro Preview, and adds AWS Bedrock service tier controls. Additional fixes cover Telegram, Slack threads, Discord group chats, startup performance, backups, Windows/macOS issues, Docker cleanup, and security, alongside guidance to back up and test before updating.00:00 OpenClaw 5.9 Overview00:47 Beta Warning and Roadmap01:22 Discord Voice Overhaul01:44 Agent Proxy Details03:36 iMessage Catch Up Mode04:36 Breaking Change Blue Bubbles05:14 WeChat and Model Updates05:58 CLI and Platform Fixes06:33 Community and Tutorials Plug07:04 Major Bug Fix Roundup09:43 How to Update Safely11:13 Final Wrap Up

237 Ways to Use Hermes Agent for Free (Automate Email, Build Websites, Fix Buggy AI Tools)The video showcases a curated list of 237 real-world Hermes Agent use cases and demonstrates how non-developers can set up automations step by step. Key examples include scheduling Hermes to summarize an email inbox and post the digest to Slack or Discord, having Hermes research you online and deploy a landing page using tools like Firecrawl and Netlify, and using Hermes’ systematic debugging skill to troubleshoot a buggy local OpenClaw setup by referencing GitHub issues and terminal logs. It also highlights Hermes Desktop, a free Mac app that provides a UI to manage sessions, profiles, models, tools, memory, and chat. The script argues Hermes is a 24/7 AI employee with memory and autonomous actions, addresses common objections, and promotes a full guide and community in the AI Profit Ballroom.00:00 237 Free Use Cases00:53 Use Case Library Tour01:37 Email Summary to Slack02:10 Ask Hermes to Build03:59 Auto Landing Page Deploy04:43 Fixing OpenClaw Bugs06:50 Hermes Desktop UI08:30 Categories and Recap09:19 Limiting Beliefs Busted10:14 Full Guide and Offer12:00 Live Q&A and Wrap

Build a Perfect AI Memory System (Hermes Agent + Obsidian + Omi) — Free SetupThe script explains how to make a Hermes Agent far more useful by giving it persistent memory using three free tools: Hermes Agent, Obsidian, and Omi. Omi runs in the background recording screen and microphone activity to generate daily “memories,” then syncs them into an Obsidian vault as readable markdown notes; Hermes can then read those local files to understand your goals, projects, schedule, and preferences without re-explaining context each session. The presenter demonstrates syncing to increase the memory count and shows how this added context helps Hermes suggest personalized improvements, dashboards, and automations like daily digests, memory cleanup, content idea extraction, and weekly performance reports. The video addresses common objections (complexity, manual upkeep, cost, and needing memory) and introduces the “Infinite Context Engine” framework, plus mentions a guide, prompts, and community/coaching resources in the AI Profit Boardroom.00:00 Perfect Memory System01:03 How the Setup Works02:43 Omi to Obsidian Sync03:07 Chatting With Memories04:08 Hermes Reads Your Vault05:25 Automation Ideas From Logs07:06 Why Memory Beats Smarts08:02 Three Free Tools Explained09:41 Common Objections Debunked11:43 Infinite Context Engine12:36 Guide and Community Offer14:29 Live Q&A Wrap Up

Build a Custom AI Content Rewriter Automation (No Code) + 4 Fixes for Repetitive AI OutputThe video shows a live, real-time build of a no-code AI automation that rewrites existing content for any audience or niche in seconds using Claude and a few prompts. The creator walks through a community member’s request inside the AI Profit Boardroom, tests her original case-study rewriting prompt, notes issues with messy and repetitive outputs, and then improves the prompt to be more relevant and actionable. Key fixes include adding important instructions at the top of the prompt, giving the AI a list of repetitive elements to avoid, using Claude instead of ChatGPT for better writing, and creating a Claude project with example files and custom instructions that specify what to avoid. It ends with an invitation to post automation requests and join the AI Profit Boardroom for coaching, community, and updated trainings.00:00 Build AI Automation Live00:44 Member Request Overview01:46 Testing The Prompt02:24 Rewriting Approach Shift03:20 Four Prompt Fixes04:57 Daily Builds In Community05:28 Join AI Profit Boardroom05:51 Courses And Daily Updates06:15 Final Link And Wrap

Make Hermes Agent 10x More Powerful: Autonomy Settings, Local LLMs, and Parallel Agent SwarmsThe video explains how to upgrade Hermes Agent from a basic chat tool into a more autonomous system by adjusting key settings and workflows shared in a Q&A from the AI Profit Boardroom community. It covers solutions for Mac Mini performance issues by running Hermes in the cloud (e.g., Hostinger), and addresses concerns about agents feeling non-proactive by editing the soul.md file to change how the agent thinks and responds, plus using /goal for an autonomous task loop. The script also shows how to run Hermes on Windows/Mac, switch models with /model, and connect to local LLMs via LM Studio or Ollama. It demonstrates running multiple agents in parallel using Hermes Workspace (swarm feature), outlines using profiles for different Telegram groups, compares Hermes vs OpenClaw, and ends with an invitation to join the AI Profit Boardroom for coaching, tutorials, and community support.00:00 Hermes Agent Upgrade00:54 Hosting Performance Fixes01:38 Autonomy Problem Setup03:09 Soulmd Prompt Tuning05:26 Goal Loop Automation06:37 Local Setup Basics07:03 Local LLM Model Switch08:21 Parallel Agent Swarms10:57 Hermes Versus OpenClaw13:12 Workspace UI Tour15:22 Telegram Dedicated Agents16:17 Self Hosted Company Agent17:34 Wrap Up And Community

Elon Just Gave Claude 220,000 H100s: Anthropic’s Compute Surge, Mythos, and What Changes for BusinessThe script explains how Anthropic’s recent compute constraints behind Claude—rate limits, peak-hour slowdowns, and interruptions—are being rapidly eased after Anthropic signed a live deal to use SpaceX’s Colossus-1 GPU cluster in Memphis (over 300 MW and 220,000 NVIDIA H100s). As a result, Anthropic doubled Claude Code five-hour rate limits for paid plans, removed peak-hour reductions, and significantly increased Opus API rate limits. It argues Elon Musk’s motivation is largely economic (idle GPUs after xAI moved training to Colossus-2) and strategic against OpenAI. The script also covers Anthropic’s broader infrastructure deals (Amazon, Google/Broadcom, Microsoft/NVIDIA, Fluid Stack, and reported Google Cloud spend), enterprise ambitions, and the unreleased Mythos model’s security-testing capabilities, plus related government controversy and implications for business workflows and AI coding competition (including Cursor).⁠00:00⁠ Elon Powers Claude⁠00:43⁠ Claude Compute Crunch⁠01:47⁠ SpaceX Colossus Deal⁠03:45⁠ Why Elon Helped⁠05:00⁠ Business Impact Boost⁠06:54⁠ Mythos Security Leap⁠08:48⁠ What It Means Now⁠10:11⁠ Cursor And GPU Wars⁠11:24⁠ Stop Waiting Start Building⁠12:57⁠ Final Takeaways

Automate Anything with ChatGPT: Build Custom AI Agents Fast

Learn how to save hours every week by building custom ChatGPT automations for your business tasks. This video demonstrates a live build of a client proposal generator using a unique strategy to optimize AI performance.

00:00 - Intro

00:26 - Custom Automation Strategy

01:17 - Setting Up a Custom GPT

01:54 - Using Claude for Expert Prompts

02:47 - Configuring the Automation

03:24 - Live Testing: Proposal Generator

03:58 - Recap & Community Access

Hermes Workspace: The Ultimate Command Center for AI Agents

Transform your AI agents from simple chat interfaces into a powerful command center with Hermes Workspace. Learn how to manage agent swarms, schedule tasks, and give your AI long-term memory with no coding required.

00:00 - Intro: Why you need a Workspace

01:07 - Installing Hermes Workspace

02:12 - Terminal vs. Workspace UI

04:52 - Dashboard & File Management

06:13 - Hermes vs. Aon UI

08:10 - Automation, Jobs & Kanban

09:14 - Mastering Swarm Mode

10:20 - Smart Routing & Memory

14:59 - The Agent Empire Framework

Run Hermes Agent for FREE! (New Owl Alpha Model Setup)

Learn how to set up and run the powerful Hermes Agent completely for free using the brand-new Owl Alpha model via OpenRouter. This guide shows you how to automate your workflows without writing a single line of code, even if you are a total beginner.

00:00 - 00:00 - Intro: The Hermes Agent Upgrade

01:23 - How to Install Hermes Agent

02:15 - Connecting Free OpenRouter APIs

03:41 - Setting Up the Owl Alpha Model

05:00 - The Power of Self-Improving Agents

06:40 - Owl Alpha vs. Traditional Models

07:50 - AI Agent Myths Debunked

08:34 - 30-Day AI Business Roadmap