AI News Today | Julian Goldie Podcast

Julian launches a new daily update series to document what he’s working on, what’s working, what isn’t, and what he’s learning about AI, inviting viewers to leave questions he will answer in future episodes. He shares progress on growing his Skool community, AI Profit Boardroom, started from zero in February last year and now top five all-time in its category with 173K MRR, plus 186 pages of testimonials. He demos ongoing development of an Agent Operating System built inside Claude, updated daily with features like Hermes Blank Slate, loop engineering, NotebookLM research updates, and Fusion benchmarking. He also shows Goldie Bench, a leaderboard where Claude tracks builds and judges model outputs, with Fusion currently leading. He discusses creating guides, answering community questions via long live streams, automating B-roll with multiple tools, and notes AI avatar videos outperform his human videos, while this channel will remain human-only.00:00 Daily Update Format01:02 Growing Skool Community02:00 Agent OS Live Builds03:22 Fusion Model Testing04:40 Goldie Bench Leaderboard07:12 Guides and Community Q&A07:54 Automated B-Roll Pipeline08:10 Avatar Videos Outperform10:27 Voice Improvements Ahead10:47 Human Only Channel Plan11:10 Join the Community11:40 Final Sign Off

Hermes Jarvis: A Real-Time Voice Agent Built on Hermes + Obsidian (Daily Briefings, Wake Word, Fast API)The script demos a real-time, voice-activated version of Hermes called Hermes Jarvis that can respond instantly, open apps like Google and Obsidian, and deliver daily briefings using memories stored in an Obsidian vault, including open items, recent work, what’s on the user’s mind, and news headlines with saved briefing history. The narrator shows conversation history, built-in features (including a meditation app), wall mode on a separate monitor, wake word activation, voice switching, link-reading from chat, and the ability to interrupt Jarvis mid-speech. They explain the system was iterated for weeks using Claude and Claude Desktop and note ChatGPT real-time API replaced ElevenLabs due to speed. The episode ends by inviting feature requests and promoting access to the full setup via the AI Profit Boardroom.00:00 Jokes and Languages00:44 Opening Obsidian Briefing01:40 Hermes Jarvis Demo03:00 How It Was Built03:28 Speed and Tooling Tips05:15 Architecture and Features06:26 Interrupt and Wake Word07:20 Build Voice Agents Now07:27 Join the Community08:06 Wrap Up

How to Use GLM 5.2 for Free on Zed AI (Plus Benchmarks vs Opus 4.8)The video explains how to access and use the open-source GLM 5.2 model for free through Zed AI (z.ai), noting token limits and showing how to select GLM 5.2 in chat or agent mode, enable web search, attach images, and switch between high/max and thinking/non-thinking settings. The creator describes GLM 5.2 as a frontier-level Chinese model with a million-token context window, released June 14, available as open weights on Hugging Face, and shares benchmark results (21 tasks, 8.23/10 on Goldy Bench) alongside comparisons where it can outperform Claude Opus 4.8 on UI/design tasks and beat Kimi K 2.7. Examples include generating playable 3D and open-world games, websites, and a working operating system with apps. They note Zed AI can be slow, recommend using a CLI via an Agent OS, and promote the AI Profit Boardroom community for tutorials and setup.00:00 Free GLM 5.2 Access00:18 Zed AI Setup Tour01:08 Agent Mode Build Demo01:27 Why GLM 5.2 Matters01:49 Benchmarks and Specs02:36 What It Can Build03:59 Full OS Example04:47 Best Way to Use It05:11 Opus vs GLM Showdown06:53 Tradeoffs and Self Hosting07:56 GLM vs Kimi Comparison09:07 Open Source Turning Point10:10 Community and Tutorials Pitch11:49 Wrap Up

Hermes Agent Blank Slate Setup Mode: Build a Faster, Update‑Proof AI AgentThe script explains Hermes Agent’s new Blank Slate Setup Mode, which lets you build an AI agent from the ground up with only the bare minimum (model, files, terminal) and manually enable tools later. It contrasts this with the old “fully loaded” setup where every agent boots with many capabilities and can become slower after updates, citing OpenClaw’s decline as an example. Hermes now offers Quick Setup, Full Setup, and Blank Slate, launched via typing “Hermes setup” in the terminal, with tools added later through “Hermes tools/skills” (e.g., skill opt-in). Benefits highlighted include faster performance (especially on weaker devices), more security, fewer tokens, predictable behavior, and an “update-proof” configuration that won’t load tools you didn’t choose. The presenter shows using separate agent profiles to compare blank slate vs full setups and promotes the Hermes Agent OS/community and coaching at aiprofitborne.com.00:00 Blank Slate Update01:16 Profiles Side by Side02:18 Update Proof Minimal Boot03:59 Setup Options Explained05:54 Why It Matters07:32 Use Cases and Demo08:41 Commands to Enable Tools09:23 Control for Client Work10:39 Key Takeaways Recap11:17 Agent OS Offer12:44 Wrap Up

Agent Operating System Q&A: Setup, Memory, Token Savings, Local vs Cloud, and Voice AgentsThis episode answers community questions about an Agent Operating System that keeps multiple AI agents and workflows in one place, including group chat orchestration, an idea-to-implementation pipeline, an agent Kanban, SEO and video agents, local engines, and a self-improving loop system, all supported by a shared memory layer. It contrasts the “old way” of juggling tabs, subscriptions, and lost context with the “new way” of a single, saved, synced workspace that reduces re-explaining. The host shares personal hardware and tool choices, explains that simpler setups can be best, and describes benchmarking models with a “Goldie Bench” to compare outputs. Additional topics include dictation tools, Hermes vs Claude trade-offs, ways to reduce token costs (free models/APIs/local), practical use cases, local GPU setups for high-quality generation, and options for Hermes voice agents.00:00 Agent OS Overview00:53 Old Way vs New01:36 Memory and Workflows02:03 Community Q&A Begins02:44 My Hardware Setup03:27 Paperclip to Pipeline04:11 Model Benchmarks04:54 Dictation Apps05:21 Hermes Troubleshooting07:04 Avoiding Overwhelm07:52 Cutting Token Costs08:50 Agent OS Use Cases10:03 Best Local AI Hardware11:55 Jose Customizes Agent OS13:22 Automating Substack13:53 Running Agents on VPS14:29 Hermes Voice Agents16:22 Laptop and Messaging Setup16:56 Wrap Up and Join

NotebookLM’s New Update + My Free “Instant Research Engine” Agent OS SetupThis episode covers a new NotebookLM update with three major changes: an improved chat experience with added sources and over 100 curated software skills for deeper research, new visualization for data including PDFs, images, and Excel sheets, and an agentic research companion that helps start notebooks from loose ideas and questions. It then demonstrates an “agentic operating system” built around NotebookLM to better organize notebooks, chat with source-trained notebooks, run fast or deep agentic research with citations, and generate assets in a studio such as presentations, podcasts, videos, mind maps, infographics, and flashcards in parallel. The script argues this system offers better organization, more recent cited answers, model flexibility via MCP, and can be built for free, with an optional packaged version in the AI Profit Boardroom.00:00 NotebookLM Update Overview00:51 Agent OS Dashboard Tour01:24 Why Build a Layered System02:01 Instant Research Engine Demo04:09 Library Research Chat Studio Workflow05:25 Generating Assets in Studio06:19 Research Report Example07:42 Parallel Agents Background Work08:37 Free Setup Options09:37 Output Quality Examples10:48 Join AI Profit Boardroom11:41 Community Support and Wrap Up

I Built an Agentic AI Operating System (Voice-Controlled Jarvis + Video/SEO/Music Agents)Julian demonstrates an “agentic operating system” built with Claude that connects multiple AI CLIs, agents, and tools into a single workspace with a large “memory galaxy,” voice control, and web/computer navigation (e.g., “Jarvis” opening his site). He explains how he iterates daily via long livestream coding sessions to automate tasks like Substack and to integrate free tools such as NotebookLM for research and one-click generation of videos, podcasts, quizzes, slide decks, and more. He showcases agents that automate video creation (including multi-minute edited videos with research and B-roll), SEO workflows that grew sites from zero to 220+ daily clicks, and even a drum-and-bass music agent. He also highlights local-model voice coding, a multi-model group chat, benchmark/leaderboard sites, an auto-generated guide site, token/API tracking, and plugging in new models, then promotes getting the system and support via the AI Profit Boardroom community.00:00 Agent OS Overview00:38 Voice Controlled Jarvis01:14 Why Build Daily02:54 Automating With Prompts03:17 NotebookLM Studio Tools03:48 Video Agent Automation04:38 SEO Growth Proof05:32 Music And Local Models06:43 Benchmarks And Guides08:07 Mission Control Workspace09:05 Plug In Any Model09:36 Community And Access11:13 How To Start Today11:46 Inside Profit Boardroom13:07 Final Wrap Up

Hermes Agent v0.17 “Reach” Update: Sub-Agents, Image Editing, Blueprints & Self-Improving LoopsThe script explains Hermes Agent v0.17 (“Reach”), highlighting the most actionable changes: new sub-agents that let Hermes delegate work to multiple asynchronous agents in parallel (e.g., generating multiple SEO articles at once), image-to-image editing when an image model is connected, and automation blueprints that can be copied from templates to quickly set up scheduled workflows. It also shows how to switch to Groq Composer 2.5 Fast via Groq OAuth (including through a Twitter or Groq subscription) without paying extra for APIs. The update includes easier creation and management of multiple agent profiles for different skills and models, plus “agent loops” where a builder and an impartial judge iterate until a quality score threshold is met, demonstrated with autopublished SEO content and an AI-generated video using a Kanban-based team workflow.00:00 Hermes v0.17 Overview00:49 Sub Agents Delegation01:55 Image Editing Upgrades02:46 Automation Blueprints Templates03:45 Free Groq OAuth Model04:42 Profile Builder Setup06:07 Agent Loops Explained06:44 Loop Method One Demo08:27 Loop Method Two Kanban09:43 More Features Jarvis10:51 Agent OS Offer Outro

Hermes v0.17 “Reach” Explained: iMessage, Async Sub‑Agents, Image Editing, Blueprints & Agent ProfilesThe script walks through Hermes v0.17 (“Reach”) and how to update it via the dashboard or terminal, then explains the main changes: Hermes can now send/receive iMessages; it joins the Raft network via a bundled adapter; the desktop app adds native OS notifications and live sub-agent watch windows; and asynchronous sub-agents let a lead agent fan out tasks to multiple workers and return combined results. It also covers a new image editing skill (not just generation) across several providers, automation blueprints for scheduling tasks without understanding the underlying syntax, and adding Cursor’s Composer model via an X subscription. The update introduces a full profile builder for managing multiple agent profiles with custom skills and instructions, an overhauled skill browser, improved memory and messaging/UI upgrades, and loop engineering with a builder/judge cycle for automated quality control.00:00 Hermes 0.17 Overview00:20 How to Update Hermes00:53 iMessage Reach Feature01:22 Raft Network Gateway01:52 Desktop App Improvements02:31 Async Sub Agents Explained04:10 Image Editing Skill04:43 Automation Blueprints06:41 New Models via X07:22 Profile Builder Workflows09:47 Skill Browser Overhaul10:55 Memory and Small Updates11:19 Loop Engineering Quality Control12:59 Wrap Up and Community Plug

North Mini: The New Free AI Model for Agentic Coding

Discover how to use North Mini, Cohere's new free agentic coding model, with the Hermes agent to build and run tools for zero cost. Learn how to set it up via the Open Router API or locally with Ollama to save your premium tokens for high-level tasks.

00:00 - Intro to North Mini

00:55 - How to Access North Mini

01:18 - Setting up Hermes Agent

01:39 - Running Locally with Ollama

02:45 - Model Benchmarks & Performance

04:07 - Creating AI Agent Profiles

05:21 - Token Management Strategy

07:31 - Building with Free Agents