ChatGPT voice doesn't just respond to you: it operates your computer in parallel
ChatGPT's voice interface can now operate a user's computer in parallel, handling tasks like booking flights and hotels in the background while the user continues with other work. The user demonstrates asking the AI to check their calendar, find travel options, and book accommodations for a Paris offsite, with the AI managing browser automation to complete these logistical tasks autonomously.
Summary
The transcript showcases a demonstration of ChatGPT's voice capabilities with computer operation features. The user initiates a voice interaction and asks the AI to assist with logistical planning for a work offsite in Paris. Specifically, the user requests help booking flights and a hotel, and wants the AI to check their calendar to determine availability for potentially extending the stay through the weekend.
The AI confirms it can see the offsite details (a DX team event in Paris) and proposes a plan returning Monday, August 31st. The user then directs the AI to use a tool called "Nivan" to spin up a background task for travel planning and hotel selection, with the user indicating they'll review and approve the final booking.
During this interaction, the AI begins executing the task in real-time, using a Chrome browser window to search flight and hotel options. The key innovation highlighted is that this task execution happens in parallel—running in the background without interrupting the conversation. The user expresses appreciation for not having to manually handle these logistical details, emphasizing that the automation of routine planning tasks provides value through time savings and reduced cognitive load.
Key Insights
- ChatGPT's voice interface can operate the user's computer in parallel, executing browser-based tasks like flight and hotel searches simultaneously while maintaining conversation
- The AI can access and check the user's calendar to determine availability for travel dates in relation to scheduled events
- The system uses a tool called Nivan to spin up background tasks that run independently, allowing the user to review results before approving final bookings
- The AI can autonomously navigate browser windows and research travel options without explicit step-by-step instructions for each action
- Users perceive significant value in having routine logistical tasks automated, as it eliminates manual work they previously had to handle themselves
Topics
Transcript
[0:00] So, I'm just going to trigger voice. All right, how's it going? >> I'm listening. Go ahead. >> I'm hoping you can help me handle a few logistical things right now. Can you see the offsite I've got pulled up in Slack? >> Yep, it's the DX team offsite in Paris. >> So, I'm hoping you can help me book my flights and a hotel for the Paris offsite. I'm also thinking about sticking around for the weekend. Could you maybe like check my calendar, see what my availability is like? >> I'll check your calendar against the offsite dates and then look at travel options. The simplest plan is returning Monday, August 31st. [0:30] >> Why don't you…
Full transcript available for MurmurCast members
Sign Up to AccessMore from How I AI
How this OpenAI engineer uses Codex + ChatGPT Work to automate everything
Nick Bowman from OpenAI demonstrates advanced use cases of ChatGPT and Codex, including voice-orchestrated multi-threaded task management, AI-powered website creation via ChatGPT artifacts, and automated video editing for content creation. He emphasizes how these tools are becoming accessible to non-technical users through mobile and voice interfaces.
How (and why) to build a personal API
The conversation explores the concept of personal APIs that store individual preferences like favorite restaurants and coffee orders, enabling others to make thoughtful gestures without asking. The discussion evolves to envision AI agents autonomously accessing these APIs to perform personalized tasks like making reservations.
Hacking an old pager with AI
A developer describes setting up an old pager as a Twitter notification device using modern cloud services. The system routes Twitter API events through Cloudflare Workers, Resend email service, and Gmail to finally deliver notifications to the pager's email address.
Opus 5: too timid?
The speaker criticizes Opus 5 for being excessively cautious and indecisive, constantly asking for human permission or approval rather than taking action. Even when faced with simple tasks like fixing a one-line merge conflict, Opus 5 deferred to the original branch owner's preferences, requiring the speaker to repeatedly push it to make autonomous decisions.
GPT-5.6's video editing via Codex is genuinely one of my favorite new workflows
A product manager describes using GPT-5.6 with Codex to automate video editing for social media clips. By simply dragging a file and providing natural language instructions, the AI generated five polished, fast-paced hype videos from a long conference talk recording, dramatically reducing the time-intensive manual clipping process.