Julian Goldie SEO

The video compares three AI code generation systems—Claude Fable 5, Hermes Mixture of Agents, and Open Router's Fusion—by testing them across 42 different builds including games, web apps, and interactive projects. Fable 5 and Hermes Mixture of Agents tie in overall performance with 3 wins each, while Fusion underperforms, demonstrating that newer frontier models don't always outperform strategically combined older models.

Google released two new AI tools—Nano Banana 2 Light for fast image generation and Gemini Omni Flash for video creation—that work together to enable rapid content production. When used as an integrated workflow, these tools can dramatically accelerate SEO-focused content creation and community management.

The video reviews Long Cat 2.0, a new open-source Chinese AI model with 1.6 trillion parameters trained on Meituan's custom chip without Nvidia hardware. Despite decent benchmark performance, hands-on testing shows it underperforms compared to GLM-5.2 in practical applications like game creation, making GLM-5.2 the stronger open-source alternative.

Google AI Studio has released a new design variations feature that automatically generates multiple layout and design options for apps and websites with a single click. This tool eliminates the need for design skills or iterative prompting, reducing what typically takes hours to seconds, and is available for free.

A detailed comparison of Claude Sonnet 5 versus GLM 5.2 AI models across game development, coding benchmarks, and UI creation tasks. The reviewer concludes that GLM 5.2 generally outperforms Sonnet 5 while being significantly cheaper, though Opus 4.8 and the forthcoming Fable 5 remain superior options.

Claude Sonnet 5 has been released as Anthropic's most agentic model, but the speaker argues it's a disappointing release that underperforms Opus 4.8 while being more expensive, making it an unattractive option for most users. The reviewer demonstrates this through benchmark comparisons and test outputs, concluding that users should stick with Opus 4.8 or wait for the incoming Fable 5 model.

Gamma, an AI design tool used by nearly 100 million people, is now integrated into ChatGPT as a native app, allowing users to create professional presentations, documents, and web pages without leaving the chat. The integration enables users to transform rough notes, training documents, and ideas into polished decks by simply conversing with ChatGPT, which handles the writing while Gamma handles the design.

Julian Goldie demonstrates how to run Qwythos 9B, a free 5.6GB local AI model on your Mac using Ollama, which can be integrated into an agentic operating system for private, offline AI tasks. While smaller than frontier models, it can effectively write, reason, and build applications locally without cloud connectivity or token costs.

The speaker demonstrates how to integrate GLM 5.2 into Claude Code using Ollama to create a cost-effective alternative AI development setup. This system combines Claude Code's agentic capabilities with GLM 5.2's brain, syncs with Obsidian for memory management, and enables building apps, games, and websites while maintaining a fraction of the cost of standard Claude subscriptions.

Ornith 1.0, a new open-source AI agent from Deep Reinforce, has achieved a score of 82.4 on SWE-Bench, surpassing Claude Opus 4.7. The model introduces self-scaffolding reinforcement learning, allowing it to build its own problem-solving framework without human-built instructions, and is available in four versions ranging from 9B to 397B parameters.

This video answers community questions about building an Agent Operating System (Agent OS) that combines multiple AI agents like Claude and Hermes with tools like Obsidian for memory management. The speaker covers practical implementations including multi-agent orchestration, video/animation agents, lead generation automation, and GLM 5.2 model optimization.

Hermes Agent released a major update enabling concurrent multi-agent Kanban operations without freezing. The update allows teams of agents to work in parallel on tasks across multiple boards, exemplified through a content factory that auto-deploys SEO articles to websites.

This video addresses common FAQs about Hermes, a free open-source AI agent, covering how to manage multiple tasks, how it compares to Claude Co-work, and strategies for reducing API token costs. The presenter demonstrates features like the Kanban board, multiple agent profiles, memory systems via Obsidian, and OAuth-based model integrations. The content is aimed at users of the 'AR Profit Boardroom' community.

The video introduces Anthropic's new Claude CLI (Ant CLI), explaining how it provides a simpler way to access Claude's API without writing code. The presenter demonstrates how it differs from Claude Code, outlines key business use cases, and shows how they've integrated it into their 'Agent Operating System' to manage AI agents in the cloud.

MiniMax M3 is a newly released open-weight AI model from Shanghai-based MiniMax that combines coding, long-context reading (1 million tokens), and multimodal vision capabilities. The video explores how these three features can automate technical SEO, content creation, and site audits. Despite some caveats about self-reported benchmarks and hardware requirements, the presenter positions M3 as a significant milestone in the closing gap between open and closed AI models.

The video introduces Pamelai (also referred to as Pameli/Pexel in the transcript), a free Google AI tool that automates brand building including website creation, AI-generated photo shoots, ad campaigns, and brand books. The presenter walks through each feature step-by-step, showing how businesses can build a complete brand identity without technical skills. The tool uses a 'business DNA' system to capture brand style and generates marketing assets through plain-language instructions.

Claude Code, an AI coding tool, can now be used for free by routing it through a free open-source version called 'free Claude Code' that connects to free models via OpenRouter. The setup can be enhanced further by integrating it with Agent OS and Obsidian for persistent memory and multi-agent coordination. The stack is expected to grow more powerful as new free models are released regularly.

The speaker demonstrates a multi-platform SEO system combining AI tools (Hermes and Claude) to achieve 'omnipresence' across Google, AI search engines, and social platforms. The core argument is that winning AI citations now requires ranking across many surfaces simultaneously rather than optimizing a single page. The system uses an 'Agent Operating System' to automate content creation across blogs, images, videos, and social media at scale.

The presenter compares Hermes Agent Desktop app against a custom Agent Operating System, arguing that the desktop app is too limited for power users. The Agent OS wins on customization, multi-agent orchestration, and workflow flexibility, while Hermes Desktop is positioned as a beginner-friendly but siloed single-agent tool.

The video introduces a free method using Obsidian, a markdown-based notes app, to create a shared memory system for AI tools like ChatGPT and Claude. By pointing multiple AI agents to one centralized Obsidian vault, users avoid repeatedly re-explaining context. Notes can even be captured automatically, ensuring all AI tools operate from the same knowledge base.