Hermes Agent V0.18 Just Changed AI Agents Forever!

Claude Fable 5 is back!

Claude Fable 5 Is Back: 42 Builds, Real-World Tests, Limits, and Better AlternativesThe script reviews Claude’s Fable 5 after its return, showing results from 42 builds and how to access it by selecting Fable 5 in Claude’s model list. It notes Fable 5 is included in a subscription only until July 7, after which it may require extra paid credits, and it sometimes auto-switches to Opus 4.8—especially on science-related prompts. The creator demonstrates strong coding and project-building speed (including a web “operating system”) but highlights weaknesses such as poor web UI output, buggy first builds, and inconsistent instruction-following compared with a custom-trained Opus 4.8. Side-by-side tests show panel approaches (Hermes Mixture of Agents, Fusion, Sakana Fugu) can outperform Fable 5 on some games and simulations, and the video promotes access to these systems and tutorials via the AI Profit Boardroom community.00:00 [https://www.youtube.com/watch?v=IyhBvFh3VCI] Fable 5 Returns00:32 [https://www.youtube.com/watch?v=IyhBvFh3VCI&t=32s] Access and Pricing Window01:15 [https://www.youtube.com/watch?v=IyhBvFh3VCI&t=75s] Showcase Web OS Build01:38 [https://www.youtube.com/watch?v=IyhBvFh3VCI&t=98s] Panels vs One Shot Tools02:08 [https://www.youtube.com/watch?v=IyhBvFh3VCI&t=128s] UI Weaknesses and Bugs03:15 [https://www.youtube.com/watch?v=IyhBvFh3VCI&t=195s] Tutorial Skill Compliance04:33 [https://www.youtube.com/watch?v=IyhBvFh3VCI&t=273s] Backlash and Model Switching05:31 [https://www.youtube.com/watch?v=IyhBvFh3VCI&t=331s] Side by Side Build Tests08:07 [https://www.youtube.com/watch?v=IyhBvFh3VCI&t=487s] Alternatives and Benchmarks08:41 [https://www.youtube.com/watch?v=IyhBvFh3VCI&t=521s] Community and Training Offer09:52 [https://www.youtube.com/watch?v=IyhBvFh3VCI&t=592s] Wrap Up and Links

Hermes Agent V0.18 Just Changed AI Agents Forever!

Hermes Agent v0.18 “Judgment” Update: Mixture of Agents, /goal Loops, /learn Skills + Proof-of-WorkThis episode breaks down the Hermes Agent v0.18 “Judgment” release and demonstrates key additions, especially the new Mixture of Agents system that fuses outputs from multiple models (e.g., Claude Opus 4.8 and GPT 5.5) to improve quality, with results shown on Goldie Bench and described as a one-shot workflow that can take 10–15 minutes per run. It covers improved /goal “goal mode” with a judge-driven loop that verifies work against a definition of done, plus proof-of-work for coding by running project checks instead of accepting “done” claims. The script also highlights /learn for turning guides or repos into reusable skills, /journey for a timeline of what Hermes has learned, background fan-out for asynchronous sub-agents, three ways to update Hermes, and how these features are organized inside the creator’s Agent OS and AI Profit Boardroom system.00:00 [https://www.youtube.com/watch?v=I07nSe9Y1dc] Hermes V0.18 Overview00:25 [https://www.youtube.com/watch?v=I07nSe9Y1dc&t=25s] Mixture Of Agents01:34 [https://www.youtube.com/watch?v=I07nSe9Y1dc&t=94s] Benchmarks And Tradeoffs02:58 [https://www.youtube.com/watch?v=I07nSe9Y1dc&t=178s] Goal Mode Looping04:15 [https://www.youtube.com/watch?v=I07nSe9Y1dc&t=255s] Why Use Agent OS05:01 [https://www.youtube.com/watch?v=I07nSe9Y1dc&t=301s] Learn And Journey06:30 [https://www.youtube.com/watch?v=I07nSe9Y1dc&t=390s] Updating And Fan Out07:50 [https://www.youtube.com/watch?v=I07nSe9Y1dc&t=470s] Delegating Sub Agents09:15 [https://www.youtube.com/watch?v=I07nSe9Y1dc&t=555s] Proof Of Work10:00 [https://www.youtube.com/watch?v=I07nSe9Y1dc&t=600s] Boardroom Systems Tour11:06 [https://www.youtube.com/watch?v=I07nSe9Y1dc&t=666s] Community And Training12:21 [https://www.youtube.com/watch?v=I07nSe9Y1dc&t=741s] Final Call To Action

Agent OS + Obsidian + Free APIs + Agent Teams!

Agent OS Updates + Community Q&A: Hermes, GLM 5.2, Memory, SEO Pipeline, and Model PicksThis episode answers recent community questions about the Agent Operating System (Agent OS), which centralizes and orchestrates multiple AI agents in one place. It covers recent updates including a Hermes lead generation tool, Mixture of Agents testing, an auto-updating memory system using Obsidian, a new GLM Code section to use GLM 5.2 with agent harnesses like Claude Code, NotebookLM short video generation and research import, an expanded SEO content pipeline with OpenSEO, and plans to add Fable 5 as a default CLI when restored. The host advises staying focused with a “Focus Protocol,” recommends Agent OS for managing multiple tools, shares guidance on Docker and GitHub/data concerns, compares models (preferring Opus 4.8, GLM 5.2 over Sonnet 5), suggests SEO stacks for local businesses, and highlights community wins, customization examples, and how to join AI Profit Bomb for training, support, and the full Agent OS.00:00 [https://www.youtube.com/watch?v=nm4xNnbSI14] Agent OS Updates01:51 [https://www.youtube.com/watch?v=nm4xNnbSI14&t=111s] Focus Protocol03:21 [https://www.youtube.com/watch?v=nm4xNnbSI14&t=201s] Why Use Agent OS04:49 [https://www.youtube.com/watch?v=nm4xNnbSI14&t=289s] Docker and GitHub06:47 [https://www.youtube.com/watch?v=nm4xNnbSI14&t=407s] Model News and Picks07:52 [https://www.youtube.com/watch?v=nm4xNnbSI14&t=472s] SEO Side Gig Stack08:58 [https://www.youtube.com/watch?v=nm4xNnbSI14&t=538s] Cheaper Models Setup09:32 [https://www.youtube.com/watch?v=nm4xNnbSI14&t=572s] Community Wins Workflows11:45 [https://www.youtube.com/watch?v=nm4xNnbSI14&t=705s] Free Models OwlAlpha12:33 [https://www.youtube.com/watch?v=nm4xNnbSI14&t=753s] Themes and Customization13:41 [https://www.youtube.com/watch?v=nm4xNnbSI14&t=821s] Best Memory System14:48 [https://www.youtube.com/watch?v=nm4xNnbSI14&t=888s] Kanban Orchestration15:44 [https://www.youtube.com/watch?v=nm4xNnbSI14&t=944s] Ollama vs Hermes16:27 [https://www.youtube.com/watch?v=nm4xNnbSI14&t=987s] More Memory Advice17:22 [https://www.youtube.com/watch?v=nm4xNnbSI14&t=1042s] Custom Desks Example18:30 [https://www.youtube.com/watch?v=nm4xNnbSI14&t=1110s] Join the Community

China’s NEW Meituan LongCat 2.0 Tested!

LongCat 2.0 (Open Source) Tested: Benchmarks, Games, and GLM 5.2 ComparisonThe episode covers the official release of LongCat 2.0, an open-source Chinese agentic model revealed as the model behind the AoAlpha free API, with features like Sparse Attention, Zero Compute Experts, and MIPD. The host reviews benchmark claims (including Terminal Bench 2.1 and SWE-Bench Pro comparisons versus GPT-5.5 and Opus 4.8) and shares hands-on tests building game demos such as Dragon Realm, a Skyrim-style open world, and VoxelCraft, noting mixed results and frequent bugs. Access issues are mentioned, including difficulty using the API without a Chinese setup, so the model is tested via the website chat. A key point is that LongCat was trained on China’s Meituan chips without NVIDIA. Overall, GLM 5.2 is judged stronger in side-by-side game benchmarks, and the host promotes the AI Profit Boardroom and Agent OS setup.00:00 [https://www.youtube.com/watch?v=60es_aKUcBU] LongCat 2.0 Launch00:36 [https://www.youtube.com/watch?v=60es_aKUcBU&t=36s] Benchmarks and API Hurdles01:38 [https://www.youtube.com/watch?v=60es_aKUcBU&t=98s] Game Demos Dragon Realm02:23 [https://www.youtube.com/watch?v=60es_aKUcBU&t=143s] Goldy Bench Verdict02:43 [https://www.youtube.com/watch?v=60es_aKUcBU&t=163s] Trained Without NVIDIA03:32 [https://www.youtube.com/watch?v=60es_aKUcBU&t=212s] How to Use It03:51 [https://www.youtube.com/watch?v=60es_aKUcBU&t=231s] Eval Results vs GPT04:17 [https://www.youtube.com/watch?v=60es_aKUcBU&t=257s] GLM 5.2 Showdown06:13 [https://www.youtube.com/watch?v=60es_aKUcBU&t=373s] Final Take and Recommendation06:35 [https://www.youtube.com/watch?v=60es_aKUcBU&t=395s] Agent OS and Boardroom Plug07:37 [https://www.youtube.com/watch?v=60es_aKUcBU&t=457s] Wrap Up

New NotebookLM Video Update is INSANE!

NotebookLM Just Added 60-Second Vertical AI Video Overviews (Coming Free Soon)The script covers NotebookLM’s new feature for generating 60-second vertical short video overviews, now rolling out to Google AI Ultra and Pro subscribers and expected to reach free users soon. The creator demonstrates examples and explains that each video is generated from a specific NotebookLM notebook’s research, producing AI images, voiceover, and editing in a hands-off workflow, especially when connected via MCP to an agent operating system. They compare the short-video outputs with longer NotebookLM videos (more slideshow-like) and with alternatives like Open Montage (more cinematic) and a separate Video Agent (preferred for educational videos). Despite video quality being below human-made content, they highlight NotebookLM’s strength as a research-and-learning tool and its one-click outputs (audio, videos, slide decks, mind maps, infographics, flashcards, quizzes, tables, reports). The episode ends by promoting the AI Profit Boardroom for setup guides, trainings, and coaching.00:00 [https://www.youtube.com/watch?v=j766Vhvv8Lo] NotebookLM Shorts Update00:46 [https://www.youtube.com/watch?v=j766Vhvv8Lo&t=46s] What The Shorts Look Like01:24 [https://www.youtube.com/watch?v=j766Vhvv8Lo&t=84s] Inside Agent OS Integration02:42 [https://www.youtube.com/watch?v=j766Vhvv8Lo&t=162s] Quality Check And Tradeoffs03:00 [https://www.youtube.com/watch?v=j766Vhvv8Lo&t=180s] OpenMontage Comparison04:24 [https://www.youtube.com/watch?v=j766Vhvv8Lo&t=264s] Video Agent Alternative04:54 [https://www.youtube.com/watch?v=j766Vhvv8Lo&t=294s] NotebookLM One Click Content Suite05:56 [https://www.youtube.com/watch?v=j766Vhvv8Lo&t=356s] Shorts Vs Long Form Videos06:45 [https://www.youtube.com/watch?v=j766Vhvv8Lo&t=405s] Learning And Speed Benefits08:09 [https://www.youtube.com/watch?v=j766Vhvv8Lo&t=489s] Which Tool To Choose08:49 [https://www.youtube.com/watch?v=j766Vhvv8Lo&t=529s] Join AI Profit Boardroom09:27 [https://www.youtube.com/watch?v=j766Vhvv8Lo&t=567s] Community Training And Wrap Up