Claude Oceanus Leaks are INSANE!

China’s GLM 5.2 is OUTRAGEOUS!

GLM 5.2: China’s Open-Source Model That Builds Games, Apps & Agent Teams (Hermes Setup + Benchmarks)The script showcases China’s open-source GLM 5.2 from ZAI, highlighting projects built with simple prompts—open-world and 3D games, websites, apps, and automated video creation—assembled in a single morning. The presenter claims GLM 5.2 performs near Claude Opus 4.8 on frontier SWE benchmarks, beats GPT-5.5 and Gemini 3.1 Pro on several benchmarks, ranks highly on Design Arena, and is far cheaper while being runnable locally. They demonstrate integrating GLM 5.2 into the Hermes agent system (including a voice-activated “Hermes Jarvis”) to run teams of agents that research keywords, write and judge SEO posts, and iteratively produce and edit videos, citing traffic growth for two websites. The video ends promoting the AI Profit Boardroom’s agent operating system, setup files, prompts, coaching calls, tutorials, and community.00:00 [https://www.youtube.com/watch?v=npJ3GLF1jIw] GLM 5.2 Shock Demo01:12 [https://www.youtube.com/watch?v=npJ3GLF1jIw&t=72s] Benchmarks And Value04:04 [https://www.youtube.com/watch?v=npJ3GLF1jIw&t=244s] Open Source Breakthrough04:49 [https://www.youtube.com/watch?v=npJ3GLF1jIw&t=289s] Design Arena Surprise07:38 [https://www.youtube.com/watch?v=npJ3GLF1jIw&t=458s] Side By Side Tests08:52 [https://www.youtube.com/watch?v=npJ3GLF1jIw&t=532s] Hermes Agent Teamwork10:43 [https://www.youtube.com/watch?v=npJ3GLF1jIw&t=643s] How To Use GLM11:11 [https://www.youtube.com/watch?v=npJ3GLF1jIw&t=671s] Daily Workflow Automation12:18 [https://www.youtube.com/watch?v=npJ3GLF1jIw&t=738s] Recap And Next Steps12:38 [https://www.youtube.com/watch?v=npJ3GLF1jIw&t=758s] AI Profit Boardroom Pitch13:47 [https://www.youtube.com/watch?v=npJ3GLF1jIw&t=827s] Community And Training14:33 [https://www.youtube.com/watch?v=npJ3GLF1jIw&t=873s] Final Goodbye

Claude: NEW AI Operating System is INSANE!

I Built an Agent Operating System (No Code) That Unifies All My AI Agents in One DashboardThe presenter tours a no-code “agent operating system” they built with Claude to run and manage multiple AI agents in one dashboard, including voice-activated Hermes/Jarvis, Claude with UltraCode sub-agent teams, and Fusion, which fuses five models plus a judge and is claimed to beat Fable 5 on benchmarks; they emphasize antifragility after Fable 5 was banned by swapping in new models and tools like GroqBuild, N2 (a free API integrated into Free Claude Code with voice control and live preview), and Gemini’s managed cloud agents that can research and generate files into the workspace. The system centralizes chat switching, shared memory via an Obsidian vault, auto-saves all generated assets to a workspace/gallery, enables workflows like SEO content deployment and one-click video creation, and supports scheduling via cron management. They offer the setup and daily-updated tutorials via the AI Profit Boardroom community.00:00 [https://www.youtube.com/watch?v=xPLr9mNGF5E] Agent OS Overview01:10 [https://www.youtube.com/watch?v=xPLr9mNGF5E&t=70s] What Agent OS Means01:51 [https://www.youtube.com/watch?v=xPLr9mNGF5E&t=111s] Agents Working Together02:26 [https://www.youtube.com/watch?v=xPLr9mNGF5E&t=146s] Model Bans And Fusion03:18 [https://www.youtube.com/watch?v=xPLr9mNGF5E&t=198s] GroqBuild Landing Pages04:07 [https://www.youtube.com/watch?v=xPLr9mNGF5E&t=247s] N2 Voice Coding04:52 [https://www.youtube.com/watch?v=xPLr9mNGF5E&t=292s] Gemini Cloud Agents05:31 [https://www.youtube.com/watch?v=xPLr9mNGF5E&t=331s] Hermes Jarvis Briefings06:18 [https://www.youtube.com/watch?v=xPLr9mNGF5E&t=378s] One Dashboard Workflow07:28 [https://www.youtube.com/watch?v=xPLr9mNGF5E&t=448s] Workflows And Gallery08:27 [https://www.youtube.com/watch?v=xPLr9mNGF5E&t=507s] Persistent Memory Obsidian09:05 [https://www.youtube.com/watch?v=xPLr9mNGF5E&t=545s] Automation And Cron Jobs10:03 [https://www.youtube.com/watch?v=xPLr9mNGF5E&t=603s] Get The System Access10:30 [https://www.youtube.com/watch?v=xPLr9mNGF5E&t=630s] Community And Testimonials11:44 [https://www.youtube.com/watch?v=xPLr9mNGF5E&t=704s] Final Wrap Up

Kilo Code DESTROYS Fable 5?

How to Get Fable 5-Level Intelligence Without Fable 5: Plan With a Frontier Model, Build CheapThe episode explains how to approximate “Fable 5-level” results despite Fable 5 being taken down by using a two-phase workflow: have a frontier model create a highly pinned, decision-complete plan, then switch to a cheaper (or even free) model to build from that plan, with optional review agents for security and logic. Citing a Kilo case study, it claims identical services can be produced when different models implement the same pinned plan, with major token and cost reductions—planning with Claude Fable 5 and implementing with GPT 5.5 reportedly cut costs by 59% while still passing 15 acceptance checks. The script also notes routing plans across models if one is removed, reusing plans as assets, and mentions Fusion as another multi-model approach, plus resources available inside the AI Profit Boardroom.00:00 [https://www.youtube.com/watch?v=sb_Fl_9Q8q4] Fable 5 Is Down00:47 [https://www.youtube.com/watch?v=sb_Fl_9Q8q4&t=47s] Kilo Planning Case Study01:31 [https://www.youtube.com/watch?v=sb_Fl_9Q8q4&t=91s] Costs And Token Savings02:53 [https://www.youtube.com/watch?v=sb_Fl_9Q8q4&t=173s] Pinned Plans Explained03:31 [https://www.youtube.com/watch?v=sb_Fl_9Q8q4&t=211s] Plan Build Review Pipeline04:40 [https://www.youtube.com/watch?v=sb_Fl_9Q8q4&t=280s] How To Run It In Kilo06:35 [https://www.youtube.com/watch?v=sb_Fl_9Q8q4&t=395s] Free And Cheap Builder Models07:34 [https://www.youtube.com/watch?v=sb_Fl_9Q8q4&t=454s] Fusion Multi Model Alternative08:06 [https://www.youtube.com/watch?v=sb_Fl_9Q8q4&t=486s] Boardroom And Closing

New Hermes Subagents Update is INSANE!

Hermes Just Added Async Sub-Agents: Delegate Tasks in the Background (No More Frozen Chat)Hermes now supports asynchronous sub-agents via a new Delegate tool that can spawn multiple workers at once, running jobs in the background so chat no longer freezes. After updating Hermes (via terminal command or dashboard), you can give a lead Hermes agent a single goal and have it fan out tasks to temporary sub-agents, each with its own thread, goal, and context, dispatched in about two milliseconds using delegate task with background=true. Results return to the chat as each worker finishes, enabling parallel workflows like generating and deploying multiple SEO articles from one keyword. The script compares the old blocking, sequential approach to the new parallel “hive” model, notes you can use plain English, and mentions using different APIs per worker. It also promotes the AI Profit Boardroom’s agent operating system, training, roadmap, community, and coaching calls.00:00 [https://www.youtube.com/watch?v=2_no0_db_lU] Async Sub Agents Launch00:15 [https://www.youtube.com/watch?v=2_no0_db_lU&t=15s] Update Hermes Fast00:41 [https://www.youtube.com/watch?v=2_no0_db_lU&t=41s] SEO Funnel Demo00:56 [https://www.youtube.com/watch?v=2_no0_db_lU&t=56s] Why Background Mode Wins01:17 [https://www.youtube.com/watch?v=2_no0_db_lU&t=77s] Real Deployment Example02:15 [https://www.youtube.com/watch?v=2_no0_db_lU&t=135s] Profiles And Temporary Agents02:44 [https://www.youtube.com/watch?v=2_no0_db_lU&t=164s] How Delegate Works03:45 [https://www.youtube.com/watch?v=2_no0_db_lU&t=225s] Parallel Workers Returning Results04:25 [https://www.youtube.com/watch?v=2_no0_db_lU&t=265s] Old Versus New Workflow05:04 [https://www.youtube.com/watch?v=2_no0_db_lU&t=304s] Keeping Control And Avoiding Chaos05:31 [https://www.youtube.com/watch?v=2_no0_db_lU&t=331s] Quick Recap And Next Steps06:30 [https://www.youtube.com/watch?v=2_no0_db_lU&t=390s] Multiply Output With Boardroom07:21 [https://www.youtube.com/watch?v=2_no0_db_lU&t=441s] Community And Coaching Details07:40 [https://www.youtube.com/watch?v=2_no0_db_lU&t=460s] Final Thanks

Le Chaton Fat Just Broke the Internet...

Why AI Benchmarks are Fake (And How to Actually Test Models) A fake French AI model recently went viral for beating the industry's top benchmarks, proving how easy it is to manipulate performance data. This video explains why you should stop chasing hype-filled charts and start evaluating AI based on your own real-world business workflows. 00:00 - Intro: The Le Chatton Fat Joke 01:08 - Why AI Benchmarks Can Lie 02:42 - The Problem with Self-Reported Tests 04:18 - Real Work is the Only Benchmark 05:20 - How to Avoid AI Overwhelm 06:34 - The New Way to Evaluate AI 07:31 - 3 Key Takeaways for AI Testing 08:45 - Testing AI Systems Yourself