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.
Summary
The speaker explains that social media video clipping is a tedious workflow they perform frequently, requiring them to extract short, engaging clips from lengthy source material. They recently obtained a recording of their own talk from Coda's event about the future of product management and wanted to repurpose it as social media content. Using GPT-5.6's video editing capabilities via Codex, they simply dragged the video file into the interface and requested five horizontal hype video cuts optimized for social platforms. After providing iterative feedback specifying they wanted faster, tighter cuts with a hype video aesthetic, the AI generated polished final videos. The speaker emphasizes that this workflow would have previously required significant manual effort to identify the right moments, clip them, and perform the actual editing work. They highlight this as one of their favorite features, demonstrating how AI-assisted video editing can transform a time-consuming creative task into a streamlined process.
Key Insights
- The speaker uses AI video editing to transform lengthy conference recordings into multiple short-form social media clips through simple drag-and-drop interface and natural language instructions
- The speaker provided iterative feedback to refine the AI output, requesting horizontal orientation, hype video aesthetics, faster pacing, and tighter cuts
- The AI-generated videos were sharp and funny, suggesting the system understood both technical requirements and creative tone from the speaker's feedback
- Manual video clipping previously required significant time investment to identify the right moments and perform the actual editing work
- The speaker identifies AI video editing as one of their favorite new features, indicating high satisfaction with this particular application of AI assistance
Topics
Transcript
[0:00] I have to do a lot of social clipping. And it's really tedious to go through and clip videos. So, taking something really long and shortening it. So, recently I spoke at Coda's event and gave this talk on the future of PM and got the recording from the Coda team. And I really wanted to make it a hype video. So, all you have to do is literally drag the file in here. And I said, "Can you cut this video into five clips for social?" I gave some feedback. I said I want them horizontal. I want them hype video cuts for various parts. [0:31] I need them to be faster. I need them to be tighter.…
Full transcript available for MurmurCast members
Sign Up to AccessMore from How I AI
Running evals on your internal agents is how you keep them trustworthy over time
The evaluation of internal AI agents is crucial for maintaining their reliability. An internal eval platform allows engineers to review agent performance regularly and ensure their responses are accurate, particularly in critical areas like coding.
You don't have to review every AI-generated PR
The speaker describes an AI agent framework that automatically reviews pull requests by scoring them across six risk factors using markdown-based instructions and skills. PRs are classified as low (0-24 points), medium (25-64), or high risk (65+), with only medium and high risk requiring human approval.
Voice is the highest-bandwidth input channel for AI
Voice interaction with AI addresses the common problem of 'blank chat window syndrome' by enabling users to naturally dump context through speech rather than carefully constructed text prompts. Voice-to-voice AI interaction mirrors the experience of delegating to a human assistant, making it a higher-bandwidth and more natural way to communicate with LLMs.
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.
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.