How to Run DeepSeek V4 Flash for FREE!
A tutorial demonstrating how to use DeepSeek V4 Flash for free through Open Code and integration with agent operating systems like Hermes Agent. The speaker showcases building websites and apps using this free AI model and explains how it compares favorably to larger models despite being smaller.
Summary
The transcript covers a comprehensive guide to accessing and utilizing DeepSeek V4 Flash 0731, a newly released free tier model on Open Code. The speaker explains that DeepSeek V4 Flash is now available for free on Open Code's platform, allowing users to build and automate projects without cost. The tutorial demonstrates practical applications including website creation, landing page design, and app development using the free model integrated into an agent operating system.
A significant portion discusses DeepSeek's architectural advantages. The speaker notes that DeepSeek V4 Flash, despite being a smaller model with the same size and architecture as previous versions, has been trained differently and now outperforms larger models. The speaker references Golly Bench testing, indicating that while not yet at Claude/GPT-5 level, the latest release represents a massive improvement over previous versions.
The tutorial demonstrates multiple integration methods. Users can access DeepSeek through: (1) Open Code directly within a customized agent operating system, (2) Hermes Agent using the Open Code CLI skill, and (3) a dedicated Deep Seek Coder window with split-screen chat and preview functionality. The speaker emphasizes the importance of workspace organization and memory/context systems that allow created projects to be saved and retrieved later, addressing the common problem of losing coded projects.
The content also covers DeepSeek's open-source advantage. Unlike closed models from OpenAI and Anthropic, DeepSeek offers open weights, making it customizable and potentially more powerful for building workflows. The speaker discusses future potential, noting that DeepSeek Pro is coming and could potentially compete with or exceed Claude/GPT-5 level performance. Finally, the transcript includes extensive promotion of the speaker's AI Profit Blueprint and Agent Operating System community, explaining membership benefits, daily video tutorials, community support, and coaching opportunities.
Key Insights
- DeepSeek V4 Flash has leapfrogged larger models despite having identical size and architecture, achieving superior performance through different training methods
- DeepSeek's open-source architecture with open weights provides a significant competitive advantage over closed models from OpenAI and Anthropic
- DeepSeek Pro is forthcoming and could potentially reach Claude/GPT-5 level or exceed it, potentially changing the entire AI industry
- Open Code provides integrated workspace organization that prevents the common problem of users losing track of their coded projects
- Multiple AI agents can be orchestrated together using a shared memory and context system, allowing projects created with one agent to be transferred and used with other agents
Topics
Transcript
[0:00] The new version of DeepSeek, DeepSeek V4 Flash 0731 is now available free. I want to show you exactly how to use it. So, what you can use is Open Code. Open Code have just announced that DeepSeek V4 Flash, the new version, is now available on the free tier inside Open Code, which means that you get the massively improved version of DeepSeek for free, and you can plug it into an agent operating system, like you can see right here, to [0:30] use DeepSeek for free. So, what we actually have is we have DeepSeek V4 Flash working with V4 Flash is the new version of DeepSeek. It's been updated inside Open Code so that we can…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Julian Goldie SEO
Microsoft Fara1.5 27B NEW Browser Automation Model is WILD!
Microsoft released Phi-3.5, a family of three computer use models (4B, 9B, 27B) that automate browser tasks through vision-based clicking rather than HTML parsing. These open-weight models significantly outperform larger closed-source alternatives like OpenAI's Operator and Google's Gemini 2.0 on web automation benchmarks.
Claude Obsidian 2.0 is INSANE (FREE!)
Claude Obsidian 2.0 is presented as a free AI memory upgrade that allows users to upload files into a folder for permanent retention and linking. The system creates a knowledge graph that learns from business documents, provides sourced answers, and can be shared across teams.
Claude Agent OS is INSANE! 🤯
Julian presents a comprehensive Claude-based agent operating system that integrates multiple AI models, automated workflows, and a persistent memory system to automate daily tasks. The system runs 24/7 and uses free or existing subscriptions, combining tools like voice agents, content creation, competitor monitoring, and real-time news analysis into a single unified dashboard.
NEW ChatGPT Update is INSANE!
OpenAI released a major ChatGPT update featuring a Chrome extension called Side Chat and an improved desktop app that work together to streamline SEO research and content creation. The update allows users to analyze multiple browser tabs simultaneously, highlight text for quick answers, and convert research into finished work without constant tab switching.
This NEW AI Design Tool Changes EVERYTHING
Julian Goldie introduces Replit Design, a new AI-powered design tool launched July 29, 2026, that enables users to create professional designs without traditional design software by using ambient intelligence and one-click iterations. The tool integrates multiple AI models, built-in design references from Mobbin, brand system support, and direct integration with live product deployment on the Replit platform.