Podcast
AI News Today | Julian Goldie Podcast
Hosted by Julian Goldie · EN
Latest Podcast
188episodes
Episodes
Newest firstAll episodes
Build Anything with GLM 5.2, here's how…
2d ago00:10:14Tap to summarizeGLM 5.2 Just Dropped: Building 3D Games, an Agent OS, and Content Fast (Zed AI)The script showcases China’s new GLM 5.2 flagship model from Zed AI and what the creator has built with it within a few hours, including multiple 3D/open-world style games, an agent “operating system” with apps and a CLI integration, and visual experiments like particle galaxy/fireworks and plasma wallpapers. They explain they improved earlier projects made with Kimi K 2.7 by plugging them into GLM 5.2, and also used a Kanban-orchestrated team of AI agents to script and assemble an AI-avatar video with music and to create an SEO-optimized blog with three articles. They highlight GLM 5.2’s coding plan value, planned local/open-source availability, 1M-token context window, long-horizon performance, compatibility with existing tools, and how to access it via API and CLI.00:00 GLM 5.2 Demo Builds00:50 How The Games Were Made01:19 Agent OS And CLI Apps01:55 Video And Blog Automation02:46 Local And Open Source Plans03:34 More Fun Project Demos04:06 Specs And Ecosystem Integrations04:57 Pricing Setup And Workflow05:54 Agent OS Memory And Switching Models07:37 How To Get Started Fast08:09 Limitations And Buggy Bits08:21 Wrap Up And Recommendation08:32 AI Profit Boardroom Pitch09:30 Community Training And Support10:12 Final Call To Action
Transcribe →NEW Hermes AI Avatar Agents!
2d ago00:09:51Tap to summarizeRank #1 with AI SEO: Hermes Agent Auto-Creates, Edits & Judges Avatar Videos in One PromptThe presenter demonstrates how Hermes Agent can generate fully edited AI avatar videos from a single prompt for AI SEO, showing three examples created with Hermes plus KimiK 2.7 (including scripts, edits, camera moves, and avatar voice/face) without manual work. They explain that targeting a keyword with these videos can help rank in Google, including AI Overview/AI Mode, and show proof of rankings. The workflow uses an agent “team” (writer, editor, judge, and KimiK 2.7) managed in a Kanban board, where a judge agent scores outputs and forces iterations until quality is high; music is created via Suno API, and video creation/editing is handled with HeyGen CLI integrated into the agent system. The episode ends by offering the full setup, tutorials, and files in the AI Profit Boardroom.00:00 AI SEO Video Breakthrough00:34 Prompt Made Video Demo01:43 Second Video Preview02:12 Music and Editing Stack02:31 Ranking Proof on Google03:08 Third Video and Judge Loop03:49 Kanban Agent Workflow04:34 Tools Behind the Scenes05:32 Results and Use Cases07:51 Setup Profiles in Hermes08:24 Recap and Next Steps08:58 Get the Agent OS09:50 Final Thanks
Transcribe →Google's NEW Cloud Managed Agents are INSANE!
2d ago00:11:40Tap to summarizeGoogle’s Gemini Managed Agents API: Your Own Cloud Computer for Deep Research & Reports (Antigravity Demo)Google released a new Gemini API for cloud-managed agents, letting you run long-horizon AI tasks in a remote, stateful Linux environment without using your local machine or setting up VPS infrastructure. The script shows how the API key from AI Studio can be plugged into an agent operating system and how Claude can help wire the integration, then demonstrates managed agents producing polished, animated research reports (including a June 2026 AI automation roundup and an AI coding agents landscape with benchmarks) and SEO research briefs by browsing the live web, running code, and returning finished files to a workspace. It notes the system can require back-and-forth (early UI issues) but delivers deeper, better-presented results than a generic Claude response. The episode also promotes the AI Profit Boardroom for access to the creator’s agent OS setup, tutorials, community, and coaching calls.00:00 Gemini Managed Agents Intro00:47 Getting API Access01:31 Plugging Into Agent OS01:58 First Builds And Limits03:02 June AI Titans Report04:36 Claude Versus Managed Agents06:00 More Research Examples06:45 How The Cloud Agent Works08:56 Why It Beats Local Work09:52 Recap And Key Takeaways10:06 Agent OS And Boardroom Offer10:54 Community Coaching And Outro
Transcribe →Kimi K2.7: New Chinese AI Super Agent is INSANE!
2d ago00:11:50Tap to summarizeKimi K2.7: China’s Long-Horizon Coding Agent That Builds Games, Web OS, and AI VideosThe script showcases China’s newly released Kimi K2.7 (Moonshot) as a long-horizon agentic coding model used to build multiple playable games, visual demos, a web-based “Kimi OS” with fully generated apps, and a fully edited AI-avatar video produced by a team of AI agents. The speaker explains that results require iteration but highlights Kimi’s ability to judge its own work and improve, plus strong token limits on the coding plan as a cheaper alternative to ChatGPT/Claude. They demonstrate integrating Kimi K2.7 via API into Hermes with separate agent profiles, switching models, and using Kimi Code via terminal or within an Agent OS. They also describe multi-agent workflows with a judge agent for autonomous video creation and other content tasks, and promote the AI Profit Boardroom community for tutorials, resources, and coaching.00:00 Kimi 2.7 First Look00:26 Games Built With Kimi00:51 AI Video And Kimi OS01:38 Pricing Plans And Tokens02:44 Dragon Realm Demo03:43 Using Kimi In Hermes04:48 Agent OS And Image API05:41 Kimi Platform Features06:43 Connecting API To Hermes07:35 Claude Code Integration08:16 Long Horizon CLI Workflow09:03 Autonomous Agent Teams10:51 Join The Community
Transcribe →Claude Fable 5 + Mythos is GONE (BANNED!)
2d ago00:13:25Tap to summarizeWhy the US Government Just Banned Claude Fable 5Discover the shocking truth behind the US government's sudden ban on Anthropic's Claude Fable 5 and Mythos 5 models. We explore the alleged role of Amazon researchers in the shutdown and why relying on a single AI model is now a major risk for your workflow.00:00 - Intro: The Claude 5 Ban00:43 - The Secret Amazon Connection02:04 - How the Jailbreak Happened03:39 - Impact on Foreign Nationals05:06 - Anthropic's Safety Backfire06:36 - Gatekeeping Intelligence Theories08:10 - The Future of AI ID Verification09:51 - Own the System, Not the Model
Transcribe →Kimi K2.7 + Hermes Agent is INSANE!
3d ago00:14:52Tap to summarizeKimi K2.7 Code + Hermes Agents: Build Apps & Videos Autonomously (Full Demo)The script showcases the release of Kimi K2.7 Code and how it’s been integrated into a Hermes Agent “crew” to autonomously build, run, bug-fix, and iterate on real projects using a large context window and a flat monthly coding plan. It demonstrates a fully AI-produced video where the avatar (via HeyGen CLI), editing/design, music, voiceover, and even camera zooms are generated by orchestrated Hermes agents using Kimi K2.7, with tasks managed through a Kanban board and a “judge” agent that scores and iterates the output from 6 to 9/10. Additional examples include a 3D game and a Web OS with persistent notes, calculator, paint, and clock apps. The speaker notes some slowness for browser-use tasks but highlights strong long-horizon performance and Moonshot benchmark gains.00:00 Kimi K2.7 Drops00:26 One Sentence App Builder01:03 AI Video Made by Agents02:10 Kanban Orchestrated Workflow03:29 Demos Games and Web OS05:59 Chat Agent Speed Test07:49 Best AI Video Workflow08:33 Benchmarks and Context09:03 Setup Inside Agent OS12:29 AI Profit Vault Pitch14:03 Final Recap and Outro
Transcribe →Claude Fable + Mythos 5 is BANNED!
3d ago00:09:59Tap to summarizeBreaking: Anthropic Pulls Fable-5 & Mythos-5 After US Government Directive (What We Know)The video reports breaking news that Anthropic’s Claude models Fable-5 and Mythos-5 have been abruptly disabled after a US government directive, which reportedly suspends access for foreign nationals (including Anthropic employees), though the creator notes some users still appear to have access and is unsure why. The announcement was received at 5:21 PM ET on June 12 and provided no specific reason, but the creator suggests it may relate to alleged bypass techniques and model use for reading codebases and fixing software flaws. Anthropic says it added strong safeguards with US/UK and third-party help, believes the directive is a misunderstanding, and warns applying this standard broadly could halt frontier model deployments. The creator compares the situation to earlier incidents, notes Opus 4.8 remains available but feels like a step backward, and promotes Agent OS and the AI Profit Boardroom for switching between models and learning AI automation.00:00 Breaking Shutdown News00:44 Testing Model Access00:59 Official Directive Details01:51 Why It Happened03:46 Anthropic Safeguards Statement05:31 Compliance And Disagreement05:58 Still Available Confusion06:38 Hands On With Fable 507:56 Industry Impact Debate08:27 Watch For Updates08:58 Agent OS Promo09:58 Final Sign Off
Transcribe →New Chinese AI Model Is INSANE! (FREE & Open Source)
3d ago00:05:18Tap to summarizeN2 Pro: Free Open-Source Chinese Coding Model Beating Claude & GPT on Benchmarks (260K Context)The video introduces N2, a new free Chinese open-source model with open weights and a 260K-token context window, designed for coding and agentic workflows with strong tool/function calling. It highlights benchmark results where N2 outperforms paid APIs like Claude Opus 4.7, GPT 5.5, and DeepSeek V4 Pro on some tests (including SWE Bench), and notes it is based on Qwen 3.5’s architecture. The model is available on Hugging Face and via a free API on OpenRouter, and can be used inside agents such as Kilocode, Hermes Agent, Claude Code (via an open-source “Free Claude Code” project), OpenClaude, and Pi. The creator demonstrates configuring N2 in Hermes Agent using model profiles, compares N2 Pro and N2 Mini, and shows N2 responding faster than a Gemma 4 setup. The video ends by promoting training and resources in the AI Profit Boardroom.00:00 Free N2 Model Reveal00:29 Benchmarks and Specs00:58 Where to Get It Free01:24 Setup in Hermes Agent02:01 Use with Claude Code02:16 What You Can Build02:32 DeepSeek Comparison02:58 Use Cases and Variants03:28 Speed Test vs Gemma04:18 Wrap Up and Next Steps04:30 AI Profit Boardroom Pitch05:17 Final Thanks
Transcribe →Hermes: Agent OS + Obsidian + Kanban + Paperclip
3d ago00:14:45Tap to summarizeTurn One Hermes Agent Into a Full AI Team (Agent OS + Obsidian Memory Galaxy + Kanban vs Paperclip)The video explains how to expand a single Hermes agent into a coordinated team by plugging Hermes into an Agent Operating System, including voice control via “Hermes Jarvis,” and using Obsidian as a local, markdown-based memory vault. It answers community questions on setting up the Obsidian “Memory Galaxy” view (now built into the latest Agent OS with a markdown setup guide), when to use Hermes’ native Kanban versus Paperclip (more complex dashboards and org charts, especially for orchestrating multiple tools), and whether Hermes profile agents can collaborate via group chat, Telegram, WhatsApp, or within the Agent OS. It also covers migrating notes from OneNote to Obsidian using MCP bridges, organizing multiple clients to avoid data conflation with separate folders and Kanban boards, customizing Agent OS UI toggles, and editing each agent’s soulmd instructions to improve response quality.00:00 Build a Team of Agents00:43 Community Q&A Setup01:08 Obsidian Memory Galaxy03:34 Hermes Kanban vs Paperclip05:50 Voice Jarvis Inspiration07:37 Agents Chat Together08:52 Move Notes to Obsidian10:07 Agents in GoHighLevel10:36 Avoid Client Data Mixups11:26 Customize Agent OS UI11:54 Improve Memory Responses12:56 Wrap Up and Join Boardroom
Transcribe →How to Use Claude Code FREE with N2!
4d ago00:09:12Tap to summarizeUse Claude Code for FREE with N2 (New Agentic API) + Voice-Build Apps LiveThe video demonstrates how to use Claude Code for free by plugging in the newly released N2 agentic “mixture of experts” API via an open-source project called Free Claude Code. N2 is based on Qwen 3.5 architecture, supports text and images, is designed for coding, tool use, deep research, and long-horizon agent workflows, offers a 262K context window, and is available on OpenRouter as a free API (with occasional token limits). The presenter shows voice-operating Free Claude Code to generate apps (e.g., a to-do list, habit tracker, meditation timer), preview results, and save every build in a workspace, plus adding skills like Hyperframes for video creation. They also show N2 working in Hermes Agent and explain integrating it into an “idea factory” pipeline and a shared memory dashboard, with setup available via the AI Profit Boardroom or the open-source project.00:00 Free Claude Code Intro00:30 What Is N2 Model00:52 Setup Free Claude Code01:14 Voice Build Demo02:07 Limits And Tradeoffs02:43 Skills And Hyperframes03:10 Goldie Voice Factory03:48 Using N2 In Other Apps05:01 Workspace And Idea Pipeline06:34 Should You Try It06:59 Recap And Next Steps07:46 Shared Memory Dashboard08:26 Community And Training Offer09:11 Final Thanks
Transcribe →