AI News Today | Julian Goldie Podcast

China's NEW GLM 5.2 AI Super Agent is INSANE!

14 min · 18. juni 2026
episode China's NEW GLM 5.2 AI Super Agent is INSANE! cover

Description

Build & Automate Anything with GLM 5.2 (3 Simple Methods + Hermes Agent Workflow)The video demonstrates how to build and automate apps, websites, games, tools, and content using GLM 5.2, highlighting projects created quickly (including 3D games and an OS inside an agent OS) and emphasizing its visual quality and large token availability on the coding plan. It explains that GLM 5.2 is an MIT-licensed, open-source Chinese coding model from ZAI (Jerbo AI), available on Hugging Face, with benchmark comparisons claiming frontier-level performance versus models like Opus 4.8, GPT 5.5, and Gemini 3.1 Pro. The host outlines three ways to use it: via a CLI/dashboard for plain-English coding into a workspace, by plugging it into the open-source Hermes Agent (including voice activation and Kanban-based multi-agent workflows with a judge for iterative quality control), or by running it locally with Ollama and integrating it into tools like Claude Code and Codex.00:00 [https://www.youtube.com/watch?v=6SXf6q3aWV8] Build Anything Intro01:42 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=102s] What Is GLM 5.202:07 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=127s] Benchmarks vs Frontier03:33 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=213s] Method One CLI Build04:29 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=269s] Method Two Hermes Agent06:07 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=367s] Kanban Content Machine08:44 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=524s] Method Three Run Locally09:48 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=588s] Why This Beats Old Way11:58 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=718s] Key Takeaways Recap12:38 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=758s] Agent OS Offer13:53 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=833s] Boardroom Community Tour14:37 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=877s] Final Thanks

Comments

0

Be the first to comment

Sign up now and become a member of the AI News Today | Julian Goldie Podcast community!

Get Started

1 month for 9 kr.

Then 99 kr. / month · Cancel anytime.

  • Podcasts kun på Podimo
  • 20 lydbogstimer pr. måned
  • Gratis podcasts

All episodes

447 episodes

episode China’s GLM 5.2 VS Claude Code: Who Wins? artwork

China’s GLM 5.2 VS Claude Code: Who Wins?

GLM 5.2 vs Claude Opus 4.8 (and Kimi K2.7): Side-by-Side Coding & Game Tests + BenchmarksThe video compares GLM 5.2 against Claude Opus 4.8 and Kimi K2.7 through side-by-side creative coding tests (raycaster engines, neon city flight, racing, solar system, voxel runner, liquid-in-a-bowl interaction, and landing pages) and discusses benchmark results and practical tradeoffs. Opus 4.8 generally produces smoother, more playable outputs and leads several tests, while GLM 5.2 wins some rounds (notably a labeled, interactive solar system, voxel runner, and the liquid demo) and scores #1 on Design Arena. The script emphasizes GLM 5.2 being MIT-licensed open source on Hugging Face and available via Ollama, cheaper on a coding plan, and easier to plug into agents via OAuth, while Claude is described as stronger overall but less flexible without paid API access. It also promotes an “agent operating system” and the AI Profit Boardroom community for setup files, tutorials, and coaching.00:00 [https://www.youtube.com/watch?v=l4YplBMoMBo] GLM 5.2 vs Claude00:43 [https://www.youtube.com/watch?v=l4YplBMoMBo&t=43s] Open Source Advantages02:12 [https://www.youtube.com/watch?v=l4YplBMoMBo&t=132s] Raycaster Showdown03:21 [https://www.youtube.com/watch?v=l4YplBMoMBo&t=201s] Upgraded Raycaster04:25 [https://www.youtube.com/watch?v=l4YplBMoMBo&t=265s] Neon City Flight05:13 [https://www.youtube.com/watch?v=l4YplBMoMBo&t=313s] Racing And Solar06:19 [https://www.youtube.com/watch?v=l4YplBMoMBo&t=379s] Voxel Runner Winner07:13 [https://www.youtube.com/watch?v=l4YplBMoMBo&t=433s] Liquid Bowl Test07:41 [https://www.youtube.com/watch?v=l4YplBMoMBo&t=461s] Benchmarks Breakdown09:44 [https://www.youtube.com/watch?v=l4YplBMoMBo&t=584s] Landing Page Faceoff10:15 [https://www.youtube.com/watch?v=l4YplBMoMBo&t=615s] Final Verdict10:46 [https://www.youtube.com/watch?v=l4YplBMoMBo&t=646s] Agent OS Integration11:17 [https://www.youtube.com/watch?v=l4YplBMoMBo&t=677s] Boardroom Pitch13:19 [https://www.youtube.com/watch?v=l4YplBMoMBo&t=799s] Wrap Up

18. juni 202613 min
episode NEW Hermes Agentic Operating System is INSANE! artwork

NEW Hermes Agentic Operating System is INSANE!

Hermes Agent OS Q&A: Build a Dashboard, Sync Agents, Stop Spirals, and Automate Your BusinessThe video answers top AI Profit Boardroom questions about using Hermes Agent to build an agent operating system, including how to run a business schedule with a simple, staged approach (start with a to-do list and add one automation per week) and three options for implementing it: a dashboard in the OS, a custom built list, or a scheduled daily recap inside Hermes chat. It explains how to get multiple agents working together using a single group chat to avoid copy/paste between tools, discusses naming agents by roles or by model/API for organization, and shares a five-line pre-build workflow (goal, current state, next action, exact question) to prevent agent spiraling alongside a “pinned plan” planner/implementer approach for high quality with cheaper models. It also covers sandboxing integrations like Google Drive/email, community examples (lead gen dashboard, LinkedIn automation on free local models), and ongoing additions like Kimi K 2.7, GLM 5.2, Fusion, pipelines, Kanban, SEO and video agent automation, plus Boardroom resources, tutorials, and coaching calls.00:00 [https://www.youtube.com/watch?v=b2cqPUyVjgg] Agent OS Overview01:18 [https://www.youtube.com/watch?v=b2cqPUyVjgg&t=78s] Schedule and Dashboard Setup01:46 [https://www.youtube.com/watch?v=b2cqPUyVjgg&t=106s] Simple To Do Automations04:04 [https://www.youtube.com/watch?v=b2cqPUyVjgg&t=244s] Agents Working Together05:49 [https://www.youtube.com/watch?v=b2cqPUyVjgg&t=349s] Naming Agents and Teams07:46 [https://www.youtube.com/watch?v=b2cqPUyVjgg&t=466s] Stop Agent Spirals10:20 [https://www.youtube.com/watch?v=b2cqPUyVjgg&t=620s] Drive and Email Sandboxing11:17 [https://www.youtube.com/watch?v=b2cqPUyVjgg&t=677s] Community Builds and Feedback13:26 [https://www.youtube.com/watch?v=b2cqPUyVjgg&t=806s] New Models and Demos14:52 [https://www.youtube.com/watch?v=b2cqPUyVjgg&t=892s] Join the Profit Boardroom15:55 [https://www.youtube.com/watch?v=b2cqPUyVjgg&t=955s] Final Thanks and Outro

18. juni 202615 min
episode China's NEW GLM 5.2 AI Super Agent is INSANE! artwork

China's NEW GLM 5.2 AI Super Agent is INSANE!

Build & Automate Anything with GLM 5.2 (3 Simple Methods + Hermes Agent Workflow)The video demonstrates how to build and automate apps, websites, games, tools, and content using GLM 5.2, highlighting projects created quickly (including 3D games and an OS inside an agent OS) and emphasizing its visual quality and large token availability on the coding plan. It explains that GLM 5.2 is an MIT-licensed, open-source Chinese coding model from ZAI (Jerbo AI), available on Hugging Face, with benchmark comparisons claiming frontier-level performance versus models like Opus 4.8, GPT 5.5, and Gemini 3.1 Pro. The host outlines three ways to use it: via a CLI/dashboard for plain-English coding into a workspace, by plugging it into the open-source Hermes Agent (including voice activation and Kanban-based multi-agent workflows with a judge for iterative quality control), or by running it locally with Ollama and integrating it into tools like Claude Code and Codex.00:00 [https://www.youtube.com/watch?v=6SXf6q3aWV8] Build Anything Intro01:42 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=102s] What Is GLM 5.202:07 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=127s] Benchmarks vs Frontier03:33 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=213s] Method One CLI Build04:29 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=269s] Method Two Hermes Agent06:07 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=367s] Kanban Content Machine08:44 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=524s] Method Three Run Locally09:48 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=588s] Why This Beats Old Way11:58 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=718s] Key Takeaways Recap12:38 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=758s] Agent OS Offer13:53 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=833s] Boardroom Community Tour14:37 [https://www.youtube.com/watch?v=6SXf6q3aWV8&t=877s] Final Thanks

18. juni 202614 min
episode These 3 NEW Chinese Autonomous AI Agents are INSANE! artwork

These 3 NEW Chinese Autonomous AI Agents are INSANE!

3 New Chinese AI Agents That Build & Automate Anything (Free N2, GLM 5.2, Kimi K 2.7)The video showcases three autonomous Chinese AI agents—Next AGI’s N2 (temporarily free via OpenRouter with a ~262K context window), GLM 5.2, and Kimi K 2.7—plugged into an “agent operating system” to build and automate projects like open-world/3D games, websites, apps, and fully AI-generated videos. It demonstrates using N2 inside Free Claude Code (including voice control), organizing multiple model profiles and teams of agents in Hermes with a Kanban workflow, and adding quality control via a “judge” agent that critiques and drives iteration. The script also describes a Fusion API panel approach (combining model outputs and judging/fusing results) that benchmarks competitively, recommends GLM 5.2 as the favorite overall and N2 as the best free option, and promotes the AI Profit Board community and downloadable Agent OS bundle with prompts, tutorials, roadmap, weekly coaching calls, and ongoing updates.00:00 [https://www.youtube.com/watch?v=3vPBg-tWaGg] Meet Three AI Agents00:39 [https://www.youtube.com/watch?v=3vPBg-tWaGg&t=39s] What They Can Build01:59 [https://www.youtube.com/watch?v=3vPBg-tWaGg&t=119s] Free N2 With Claude Code02:50 [https://www.youtube.com/watch?v=3vPBg-tWaGg&t=170s] Games And GLM OS Demos03:45 [https://www.youtube.com/watch?v=3vPBg-tWaGg&t=225s] Hermes Agent Teams04:50 [https://www.youtube.com/watch?v=3vPBg-tWaGg&t=290s] Quality Control Judge Agent06:09 [https://www.youtube.com/watch?v=3vPBg-tWaGg&t=369s] Idea Factory To Gallery07:31 [https://www.youtube.com/watch?v=3vPBg-tWaGg&t=451s] Why You Need Agent OS09:25 [https://www.youtube.com/watch?v=3vPBg-tWaGg&t=565s] Benchmarks And Fusion Panel10:48 [https://www.youtube.com/watch?v=3vPBg-tWaGg&t=648s] Which Model To Pick11:15 [https://www.youtube.com/watch?v=3vPBg-tWaGg&t=675s] Get The Full System12:33 [https://www.youtube.com/watch?v=3vPBg-tWaGg&t=753s] Final Thanks

18. juni 202612 min
episode NEW Agent OS is INSANE! (Runs 3 Businesses FREE!) artwork

NEW Agent OS is INSANE! (Runs 3 Businesses FREE!)

Agent OS Q&A: Running Multiple AI Agents, Video Automation, SEO Workflows & Setup (Local vs VPS)The episode answers common questions about an Agent Operating System built for the Air Profitable community, explaining how it runs multiple agents in parallel with shared workflows using a Kanban/Hermes setup that assigns tasks to different agent profiles, and noting Hermes’ new asynchronous sub-agents feature for background delegation. It covers AI video generation options via a Studio using Groq/Minimax and free open-source Hyperframes, plus HeyGen for avatar videos. The script discusses using Hermes as a Perplexity Computer alternative and integrating Google Managed Agents API via Antigravity for cloud-based agents. It recommends running Agent OS locally for speed and privacy, shows UI customization and chat/vault management tips, advises using free cloud APIs over slow local models on Mac hardware, and promotes the AI Profit Boardroom for the zip file, tutorials, updates, and community support.00:00 [https://www.youtube.com/watch?v=m7XT7bpYFPU] Agent OS Q&A Intro00:27 [https://www.youtube.com/watch?v=m7XT7bpYFPU&t=27s] Running Multiple Agents02:28 [https://www.youtube.com/watch?v=m7XT7bpYFPU&t=148s] AI Video Generation Setup04:05 [https://www.youtube.com/watch?v=m7XT7bpYFPU&t=245s] Hermes as Perplexity Alternative05:50 [https://www.youtube.com/watch?v=m7XT7bpYFPU&t=350s] Local vs VPS Installation07:17 [https://www.youtube.com/watch?v=m7XT7bpYFPU&t=437s] Customizing the Agent OS UI08:28 [https://www.youtube.com/watch?v=m7XT7bpYFPU&t=508s] Adding Tools and Saving Chats10:05 [https://www.youtube.com/watch?v=m7XT7bpYFPU&t=605s] Best Models for Mac Mini11:31 [https://www.youtube.com/watch?v=m7XT7bpYFPU&t=691s] Hermes Desktop Troubleshooting13:11 [https://www.youtube.com/watch?v=m7XT7bpYFPU&t=791s] VPS Hosting and SEO Automations14:08 [https://www.youtube.com/watch?v=m7XT7bpYFPU&t=848s] Custom Business Workflows16:00 [https://www.youtube.com/watch?v=m7XT7bpYFPU&t=960s] Wrap Up and Join Boardroom

18. juni 202617 min