5 Ways To Use ChatGPT's New Features
The transcript demonstrates five practical applications of ChatGPT's new features, including computer use for software automation, advanced image editing, cloud browser integration for account access, voice-powered live agents, and persistent session agents for long-term user interaction tracking.
Summary
The video presents five innovative use cases for ChatGPT's latest capabilities. The first example showcases GPT6's upgraded computer use functionality, which can operate desktop applications like Blender to transform a workspace photo into a digital diorama with lighting and rendering. The second feature highlights GPT image 2.5's precise image editing capabilities, enabling users to modify specific elements like adding a cozy reading corner while preserving all other details unchanged. The third use case introduces ChatGPT Works cloud browser, a persistent online workspace that allows the AI to sign into websites and manage user accounts without requiring access to personal browsers, exemplified by checking subscription plans and creating a payment dashboard. The fourth application demonstrates GPT Live 1 API's ability to maintain real-time conversation while simultaneously conducting background research and displaying sources, illustrated through a voice-powered travel planner. Finally, the fifth example describes the new agents API with persistent session support, enabling applications like a guitar practice coach to remember user progress between sessions and provide continuity in coaching.
Key Insights
- GPT6's upgraded computer use can now operate desktop software like Blender to automate complex creative tasks such as converting photos into rendered 3D dioramas
- GPT image 2.5 enables surgical-level precision in image editing, allowing specific details to be changed while completely preserving unchanged elements in the same image
- ChatGPT Works cloud browser creates a persistent online workspace where the AI can access and manage user accounts without requiring control of the user's personal browser
- GPT Live 1 API maintains active conversation while an agent works in the background researching and displaying sources in real-time
- The new agents API supports persistent sessions that enable applications to maintain context and track user progress across multiple separate interactions
Topics
Transcript
[0:00] Here are five new ways to use the new version of ChatGpt's new features. I'm going to be trying these inside the Codeex app, so make sure you save these prompts. Number one, open Blender and build a miniature version of my workspace with this photo. Add lighting and then render it. GPT6 now has an upgraded version of computer use so it can operate software like Blender to turn my desk into like a digital diarama. Number two, show this room with a cozy reading corner. Keep everything outside of that corner unchanged. GPT image 2.5 has much more precise image editing. You can change specific details [0:34] while completely preserving the rest. Number three, check the AI…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Matt Wolfe
My BIGGEST AI Pet Peeve...
The speaker criticizes companies for announcing features before they're ready, using Claude's Co-work announcement as an example. They argue that companies should only announce features once they're fully available, not during rollout phases.
Opus 5.5 Is Crazy Good and GPT-6-Sol Launched Too
Anthropic released Claude Opus 5.5, a new state-of-the-art model that outperforms their previous best model (Fable 5.1) while being 40% cheaper and faster. OpenAI simultaneously launched GPT-6 Soul and Luna, which are cheaper and faster but less capable than their flagship Astra model, making Opus 5.5 the more impressive release of the day.
This Robot Looks DEMONIC... On Purpose?
A California company created Three Halves, a deliberately creepy-looking four-legged robot designed to perform dangerous tasks in hazardous environments like wildfires and collapsed buildings. Its anthropomorphic torso allows it to use human-designed tools, while its design features—including locked joints, stable stance, and horn-mounted cameras—prioritize safety and functionality over aesthetics.
He Built The Ultimate Spy Tool (Free and Open-Source)
Belaval Sadu created God's Eye View, a free open-source platform that aggregates real public data sources (flights, satellites, vessels, CCTV, traffic) into an interactive globe interface to provide civilian intelligence and situational awareness. The tool uses AI agents and multiple APIs to make geospatial data accessible to anyone, with applications ranging from content creation to journalism and disaster reconstruction.
ChatGPT Drew Me In Minecraft
The creator demonstrates that Claude (referred to as Astro) can autonomously control a computer and browser to play Minecraft, successfully tasking it with creating a portrait of the creator using blocks in creative mode. The AI completed the project in 1 hour and 42 minutes, proving its capability to operate complex applications independently.