/prod-by-claude created a skill for opus 5.5 using strudel + @HyperFrames_ to create live-coding music videos claude composed this example's beat + video using the skill try here: github.com/heygen-com/hyperf… // dj opus out

who doesn't love some Allman Brothers and free stuff? made this video with Opus 5.5 and @HyperFrames_ for the 3 new components I added to the catalog even the little tasks can have a good video thanks to agentic editing npx hyperframes add colorama-wipe npx hyperframes add text-match-cut npx hyperframes add extended-keyframe

muse is really killer at making podcasts!!

if you tried hyperframes, you would know the agentic video stack is being built on code-gen but SWE-bench code v.s. code-to-video that feels alive are two different things we built the Code2Video Bench, in collab w/ Google DeepMind & @Kaggle frontier labs can finally get good at agentic video tasks

Figma for video editing doesn't exist for a reason. At my company, we're building a video editor for AI. But I've been eyeing this space for years. "Figma for X" has been a popular startup pitch since 2019. And serious founders have certainly tried, with millions in funding, to make it happen for video editing. But by 2026, it's obvious that there must be a reason why none of those startups survived. Here's what I uncovered: 1. The professional video space is fragmented. Unlike in design, today's post-production teams stitch together multiple highly specialised tools: - Premiere Pro for editing - DaVinci Resolve for color grading - Frame io for feedback and review - LucidLink for sharing footage No player has managed to build an all-in-one solution because video is REALLY, REALLY HARD. A Figma for video editing would need to be competitive in all these individual segments to win. But that's a technical challenge, and it can certainly be solved with enough talent. I believe there are stronger reasons. 2. It's a vitamin, not a painkiller. I'm sure plenty of video editors would consider real-time collaboration a cool feature. But is that need strong enough to make them switch from a trusted, robust editing tool to something experimental? Probably not. And that's not hard to imagine. Take software development: that space hasn't moved to real-time collaboration either, even though solutions exist. It just doesn't improve the development workflow enough. 3. A shared timeline is a shared bottleneck. Video editing decisions are tightly connected. One editor performs a ripple delete, and suddenly the clips another editor is working on shift underneath them. Editors need room to experiment independently without disrupting each other's work. A shared timeline doesn't solve that. But there is hope! At this point, it's painfully obvious: the next generation of NLEs will store edits in a codebase instead of a structured database. If the project is saved as code, video editors can suddenly use the same tools developers have spent decades refining, starting with Git. This opens up enormous possibilities for video editing: - Open-source video projects - Iterating in branches - Safely merging the work of multiple editors - Reusing code and video compositions I'm convinced this type of collaboration fits modern post-production far better and points to an exciting future for collaborative video editing.

Introducing our Trusted Person network powered by our new Instinct-to-Instinct communication protocol. Your Instinct can now talk to other Instincts to coordinate plans on your behalf. Getting people together often involves a lot of back-and-forth: finding a time, working out the details, and following up when plans change. Instincts can now work with each other to help handle that coordination. For example: - Coordinating plans with your spouse - Planning a weekend trip with friends, including dates and arrival times - Scheduling time with colleagues and other collaborators - Hosting events with 10s or 100s of people - Organizing recurring plans like tennis, book clubs, or weekly dinners Disclaimer: Your Instinct will only be able to communicate with those in your Trusted Person network. This is the group of people who are closest to you: - Spouse - Older children and parents - Colleagues and trusted professional relationships - Small local businesses The Trusted Person network is currently available to our early access group and will be slowly rolled out across the user base over the next 24-48 hours.

we were legit amazed by GPT-live-1 and when we combined it with @HyperFrames_ and @TryLiveAvatar - and it's magical here's a demo of a real-time poker coach: - all cards & ui fully generated on the fly w hyperframes - GPT-live is the brain and voice - live avatar makes it all come to life and we open sourced everything, so anyone can build on top (and yes, the repo is agent-friendly)

Real-time AI experiences are now solved AND open sourced. We worked closely with @OpenAI to build the best framework for it, combining GPT-Live-1, @TryLiveAvatar, and @HyperFrames_ Check out the demos below and show us what you build with it. github.com/heygen-com/liveav…

via @HyperFrames_

simple ad formats are crushing on socials right now so we built a set of them into hyperframes all we need is your website our agent pulls your brand assets and fits the storyline to how you already message free for anyone to try today get started below ↓