Hermes: New AI Video Game Agent is WILD!

Fable 5 is BACK!

Fable 5 Is Coming Back Tomorrow: Export Controls Lifted, Global Access Returns (Plus New Safeguards)Anthropic announced that Claude Fable 5 will be redeployed globally starting July 1 after U.S. export controls imposed June 12 shut down access to Fable 5 and Mythos 5 for everyone due to immediate compliance needs. The controls were lifted June 30, with Fable 5 returning across Claude Platform, Claude AI, Claude Code, and Claude Cowork for Pro, Max, Team, and select Enterprise plans, included for up to 50% of weekly usage limits before shifting to paid usage credits after July 7. Mythos 5 access is being restored only to certain U.S. organizations via Project Glasswing following June 26 approval. The shutdown followed a report that Amazon researchers found a method to bypass Fable 5 safeguards; Anthropic says the bypass is now blocked in over 99% of cases and that U.S. Commerce testing agreed the new safeguards are extraordinarily strong, alongside plans for deeper government collaboration and pre-release evaluations.00:00 [https://www.youtube.com/watch?v=Ao0oaaD4dkc] Fable 5 Returns00:45 [https://www.youtube.com/watch?v=Ao0oaaD4dkc&t=45s] Global Rollout Details01:13 [https://www.youtube.com/watch?v=Ao0oaaD4dkc&t=73s] Usage Limits and Credits01:54 [https://www.youtube.com/watch?v=Ao0oaaD4dkc&t=114s] Mythos 5 Partial Restore02:32 [https://www.youtube.com/watch?v=Ao0oaaD4dkc&t=152s] Why It Was Shut Down03:46 [https://www.youtube.com/watch?v=Ao0oaaD4dkc&t=226s] Timeline and Big Picture06:19 [https://www.youtube.com/watch?v=Ao0oaaD4dkc&t=379s] Amazon Bypass Explained08:06 [https://www.youtube.com/watch?v=Ao0oaaD4dkc&t=486s] New Safeguards Breakdown09:11 [https://www.youtube.com/watch?v=Ao0oaaD4dkc&t=551s] Industry and Government Frameworks10:05 [https://www.youtube.com/watch?v=Ao0oaaD4dkc&t=605s] Wrap Up and Community Plug

Hermes Mixture of Agents is ABSURD!

Hermes Mixture of Agents (MOA): Combine Claude + GPT with an Aggregator to Beat Frontier ModelsThe script explains Hermes’ Mixture of Agents system, which lets you combine multiple models (e.g., Claude Opus 4.8 and GPT-5.5) into a panel and choose an “aggregator” model to fuse their outputs, treating the mix as one virtual model. The presenter demos results like generating a Windows-style OS and building games, showing side-by-side comparisons where the mixture outperforms a single model, and notes they tested 42 builds viewable on Goldie Bench. It describes how MOA 2.0 works under the hood (private analysis by models, then an aggregator writes the final answer and runs tools), switching mixes with /MOA, and claims of benchmark gains (8% over Opus 4.8, 11% over GPT-5.5). Downsides include slower runtime, API reliance, and technical setup, which they simplify via their Agent OS dashboard, also featuring Fusion and Sakana-style panels, automations, memory, and access via their paid community with tutorials and coaching.00:00 [https://www.youtube.com/watch?v=mKMo4WVdLVI] Mixture of Agents Intro00:33 [https://www.youtube.com/watch?v=mKMo4WVdLVI&t=33s] How the Panel Works01:27 [https://www.youtube.com/watch?v=mKMo4WVdLVI&t=87s] Bench Tests and Demos02:13 [https://www.youtube.com/watch?v=mKMo4WVdLVI&t=133s] Side by Side Game Results03:23 [https://www.youtube.com/watch?v=mKMo4WVdLVI&t=203s] Tradeoffs and Limitations04:02 [https://www.youtube.com/watch?v=mKMo4WVdLVI&t=242s] Making MOA Easy to Use04:45 [https://www.youtube.com/watch?v=mKMo4WVdLVI&t=285s] MOA 2.0 Explained05:28 [https://www.youtube.com/watch?v=mKMo4WVdLVI&t=328s] Fusion and the Bigger Trend06:34 [https://www.youtube.com/watch?v=mKMo4WVdLVI&t=394s] Stop Chasing Models07:10 [https://www.youtube.com/watch?v=mKMo4WVdLVI&t=430s] Three Systems and Why They Win07:37 [https://www.youtube.com/watch?v=mKMo4WVdLVI&t=457s] How to Use It Today08:19 [https://www.youtube.com/watch?v=mKMo4WVdLVI&t=499s] Agent OS and Community Pitch09:50 [https://www.youtube.com/watch?v=mKMo4WVdLVI&t=590s] Wrap Up and Goodbye

Claude Sonnet 5 is HERE!

Claude Sonnet 5 Review: More Expensive, Worse Than Opus 4.8? (Benchmarks & Agent Tests)The video reviews Anthropic’s newly released Claude Sonnet 5, described as more agentic and capable of planning and tool use, but argues it underperforms Opus 4.8 on benchmarks (including agentic coding) while costing more. The creator shares Goldy Bench examples Sonnet 5 generated (a ray caster maze, a broken galaxy orbit test, a synthwave background, and a crypt game), noting some outputs look good but others fail. Side-by-side comparisons show mixed results versus GLM 5.2, with GLM succeeding on tasks Sonnet 5 fails, and tweets highlight negative reception focused on poor token efficiency and pricing. The recommendation is to keep using Opus 4.8, expect Fable 5 soon, and focus on building flexible agent systems that can swap models in and out.00:00 [https://www.youtube.com/watch?v=1Wl-4D6D5rw] Sonnet 5 Launch00:30 [https://www.youtube.com/watch?v=1Wl-4D6D5rw&t=30s] Benchmarks vs Opus01:39 [https://www.youtube.com/watch?v=1Wl-4D6D5rw&t=99s] Goldy Bench Demos02:53 [https://www.youtube.com/watch?v=1Wl-4D6D5rw&t=173s] GLM 5.2 Comparisons04:00 [https://www.youtube.com/watch?v=1Wl-4D6D5rw&t=240s] Backlash and Pricing05:57 [https://www.youtube.com/watch?v=1Wl-4D6D5rw&t=357s] Fugu Ultra Showdown07:20 [https://www.youtube.com/watch?v=1Wl-4D6D5rw&t=440s] Why Release This08:00 [https://www.youtube.com/watch?v=1Wl-4D6D5rw&t=480s] Focus on Systems09:11 [https://www.youtube.com/watch?v=1Wl-4D6D5rw&t=551s] Agent OS Pitch09:48 [https://www.youtube.com/watch?v=1Wl-4D6D5rw&t=588s] Final Verdict

Fable 5 is back in 24 hours!

Export Controls Lifted: Fable 5 & Mythos 5 Returning Tomorrow (Official Anthropic Update)The episode reports that U.S. export controls on Anthropic’s Fable 5 and Mythos 5 have been lifted, citing a tweet and Anthropic’s official June 30, 2026 announcement that access will begin being restored tomorrow (likely within 24–48 hours). It notes Commerce Secretary Howard Lutnick’s statement about working with Anthropic over two weeks to analyze and approve Fable 5, and mentions a related comment from White House Chief of Staff Susie Wiles. The host recaps the timeline: access was cut on June 16 due to flagged security concerns, reports suggested a return by late June, and the White House/Commerce/Anthropic announcements arrived rapidly on July 1. They also comment that there’s no news on GPT 5.6, argue Fable 5 is a major step up from Sonnet 5, and emphasize building resilient “agent operating systems” that can swap models and avoid workflow disruption, promoting the AI Profit Boardroom and its Agent OS, training, and coaching.00:00 [https://www.youtube.com/watch?v=-NujvRyaWn4] Export Controls Lifted01:12 [https://www.youtube.com/watch?v=-NujvRyaWn4&t=72s] Global Access Returns01:29 [https://www.youtube.com/watch?v=-NujvRyaWn4&t=89s] Sonnet vs Fable01:55 [https://www.youtube.com/watch?v=-NujvRyaWn4&t=115s] Why This Matters02:30 [https://www.youtube.com/watch?v=-NujvRyaWn4&t=150s] Official Statements03:41 [https://www.youtube.com/watch?v=-NujvRyaWn4&t=221s] How It Unfolded04:12 [https://www.youtube.com/watch?v=-NujvRyaWn4&t=252s] Previous Shutdown Timeline04:54 [https://www.youtube.com/watch?v=-NujvRyaWn4&t=294s] GPT Updates Check05:28 [https://www.youtube.com/watch?v=-NujvRyaWn4&t=328s] Focus on Systems06:39 [https://www.youtube.com/watch?v=-NujvRyaWn4&t=399s] Diversify Your Workflow07:00 [https://www.youtube.com/watch?v=-NujvRyaWn4&t=420s] Agent OS Pitch07:37 [https://www.youtube.com/watch?v=-NujvRyaWn4&t=457s] Join the Community

GLM 5.2 + Claude Code is INSANE!

Plug GLM 5.2 Into Claude Code + Obsidian (Cheaper Claude Code Harness + Agent OS Workflow)The video shows how to plug GLM 5.2 into Claude Code and Obsidian to get Claude Code’s agent harness with a cheaper “brain,” enabling app, website, game, and tool building while saving everything to a workspace and logging outputs into an Obsidian memory system for personalization and automatic organization. The creator compares GLM 5.2 to Opus, noting personal tests where GLM 5.2 produced better outputs on some tasks and offers a fallback when Claude Code is rate-limited or fails. Setup is described as simple: download Ollama, run GLM 5.2, point Claude Code at it, and use an Agent OS button to switch among agents and profiles (e.g., Paperclip, AI Agent Mastermind, Hermes). The video ends by promoting AI Profit Boarding for Agent OS access, daily updates, guides, community support, and coaching calls.00:00 [https://www.youtube.com/watch?v=-otUvuErbF0] Cheaper Claude Code Setup00:51 [https://www.youtube.com/watch?v=-otUvuErbF0&t=51s] GLM vs Opus Benchmarks01:32 [https://www.youtube.com/watch?v=-otUvuErbF0&t=92s] Install Ollama and GLM01:51 [https://www.youtube.com/watch?v=-otUvuErbF0&t=111s] Workspace and Obsidian Memory02:44 [https://www.youtube.com/watch?v=-otUvuErbF0&t=164s] Live Build Demo03:07 [https://www.youtube.com/watch?v=-otUvuErbF0&t=187s] What Is GLM Code03:46 [https://www.youtube.com/watch?v=-otUvuErbF0&t=226s] Switching Agents in Agent OS04:41 [https://www.youtube.com/watch?v=-otUvuErbF0&t=281s] Any Ollama Model Works05:20 [https://www.youtube.com/watch?v=-otUvuErbF0&t=320s] Costs and CLI Options05:44 [https://www.youtube.com/watch?v=-otUvuErbF0&t=344s] Hermes Profiles and Teams06:28 [https://www.youtube.com/watch?v=-otUvuErbF0&t=388s] Get the Full System07:01 [https://www.youtube.com/watch?v=-otUvuErbF0&t=421s] Community and Training Offer07:47 [https://www.youtube.com/watch?v=-otUvuErbF0&t=467s] Wrap Up and Thanks