Codex Just Did What Claude And ChatGPT Couldn’t (Full App, No Code)
The creator demonstrates OpenAI's Codex app, positioning it as a major upgrade over ChatGPT by showing it autonomously build a full web app, design UI screens, catch its own bugs, and generate pitch decks and launch videos — all without writing code. He argues Codex functions as an 'agent' that does work rather than just answering questions, and has switched his entire team to it.
Summary
The video opens with the creator, Vibhav, declaring he has asked his team to stop using ChatGPT in favor of Codex, framing it as the 'full version' of AI that was previously locked behind developer tools. He positions ChatGPT as outdated ('your father's AI') and Codex as the next evolution, powered by GPT-4.5 underneath and now accessible to non-developers via a downloadable Mac/Windows app.
Vibhav walks through the Codex interface, highlighting three core sections: Projects, Plugins, and Automations. He demonstrates how Plugins connect Codex to tools like Gmail, Slack, Notion, Figma, and Canva, enabling it to operate across an entire software ecosystem. His first use case is a daily automation: every morning at 9 a.m., Codex checks his Gmail, finds a specific newsletter, extracts key points, and generates a PowerPoint deck in Canva — entirely without human involvement. He frames this as saving him an hour every day.
The centerpiece of the video is building a full web app called 'Near Folk' — a platform to match people in Bangalore and San Francisco with offline meetups and founder events. Rather than immediately coding, Codex first asks clarifying product questions (user type, data source, matching logic), which Vibhav contrasts favorably against older AI tools that generate random output without seeking clarity. Codex even proposes brand name options, with Vibhav selecting 'Near Folk.'
For UI design, Vibhav uses a tool called 'Paper' connected to Codex via MCP (Model Context Protocol), allowing Codex to autonomously control Paper's canvas and draw app screens in real time — hero sections, buttons, chat interfaces, and marketplace layouts — without any human input on the design tool itself. He describes this as a brain-breaking moment: an AI driving another piece of software the way a human would.
In 'Plan Mode,' Codex maps out the full build architecture — database structure, page routes, and components — before writing a single line of code. During the build, Vibhav uses a 'Steer' feature to adjust scope mid-build without interrupting the agent. He also demonstrates leaving plain-English comments in the code (to switch from OpenAI API to OpenRouter) rather than editing code directly, showing that code literacy is not required.
The most dramatic moment Vibhav highlights is Codex autonomously catching and fixing a mobile layout bug during its own self-testing phase — no human prompt required. It identified the issue, planned a fix, implemented it, and verified the result in roughly 20 seconds while Vibhav was in the kitchen. He notes this kind of autonomous QA is something he normally has to push technical teams to do for weeks.
Using a 'Fork into Local' feature, Vibhav runs a parallel chat thread to generate launch materials simultaneously — a four-to-five slide sponsor pitch deck and an 8-second branded launch video with music and motion graphics — from a single prompt. The video closes with a live demo of the completed Near Folk app, showing functional event browsing and seat-request forms for both Bangalore and San Francisco.
Key Insights
- Vibhav argues that Codex is not just a better chatbot but a fundamentally different category of tool — an 'agent' that does things (opens files, runs software, sends Slack messages, builds apps) rather than merely answering questions, which he identifies as the core distinction from ChatGPT.
- Vibhav claims Codex behaves like a product manager rather than a code generator — before building the Near Folk app, it returned clarifying questions about the user, data source, and matching logic, which he contrasts with older AI tools that 'spit out something random' from a single prompt.
- Vibhav describes watching Codex autonomously control the Paper design tool in real time — moving the cursor, drawing UI screens, placing buttons and text — and argues this signals that 'the skill is not the design tool anymore, the skill is knowing what to ask.'
- Vibhav highlights that Codex caught its own mobile layout bug during self-testing — without any human prompt — planned a fix, implemented it, and verified the result in about 20 seconds, calling it 'not a tool, that is a teammate' and noting this level of autonomous QA normally takes weeks to get from technical teams.
- Vibhav demonstrates that plain-English comments left directly in the code — rather than actual code edits — are sufficient for Codex to understand and implement changes, using this to argue that users don't need programming knowledge, only the ability to be specific about what they want.
Topics
Transcript
[0:00] I asked my team to stop using chat GPT. If you want to stay ahead in AI, this is the video to watch because the people still using chat GPT in 2026 the way they used it in 2025, they are about to get left behind. Here is what nobody tells you about chat GPT. It is not the full version of AI. It is the easy version. There has always been a more powerful version underneath, but it was locked behind code. Only developers could use it. Last week, OpenAI changed that. They took the version developers have been using all this time and built [0:31] it into an app anyone can open powered by the latest model…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Vaibhav Sisinty
This New AI Agent Turns You Into a One-Person Company
The video showcases Axion Work, an AI agent platform by Alibaba that runs locally on your computer, through two real-world business tests: generating a market strategy for an Indian coffee brand (Drinkle/Bonhomie) and building a live Shopify dropshipping store from scratch. The creator argues this tool effectively replaces multiple business team roles — strategist, researcher, designer, and ops — for solo founders and small teams.
Why I Cancelled My Claude Code Subscription🔥
A short-form video tutorial explains how to replace Claude Code's Anthropic backend with a locally-run Qwen model via Ollama, eliminating API costs and rate limits. The presenter outlines three steps to redirect Claude Code to a local server. The video ends with a call-to-action for a setup link, WhatsApp community, and daily follow content.
Stop Using ChatGPT. Google Just Changed Everything🤯
The video introduces Gemini Spark, a Google product announced at IO 2026, which runs on dedicated Google servers rather than user devices. Unlike conventional AI tools, it continues working autonomously even when all user devices are off, learning user habits and completing tasks overnight. The presenter positions it as a paradigm shift from smart chatbots to persistent personal AI employees.
AI Just Took Over the Most Sensitive Room in Medicine🤯
A company called Conceivable Life Sciences has developed an AI-guided robotic system that autonomously performs key IVF steps, including sperm selection, egg positioning, and insemination. This technology could address the global shortage of skilled embryologists and reduce costs and wait times. While still early-stage and regulated, it marks a significant shift in AI moving from data analysis to hands-on medical procedures.
Claude Code vs. OpenCode: Which Agent is Better for 2026?🤯
A short-form video promotes OpenCode, a free open-source terminal-based alternative to Claude Code. The creator demonstrates a quick installation process and claims it handles the same tasks as Claude Code at no cost. The video ends with a call to action for links and a WhatsApp community.