Techguyver

@JJEnglert @claudeai What do you use descript for?

Motion graphics used to take me an hour per scene (or more) Now I'm creating them in 3-5 minutes — without After Effects, without Premiere, without writing a single line of code. I'm a former LA filmmaker (still PGA). My entire video stack is now 3 tools: @claudeai Code + HyperFrames (from @HeyGen) + @descript Here's how the workflow runs: 1. Drop my brand style guide into a folder (colors, fonts, components Claude reuses forever) 2. Paste a line from my Descript transcript into Claude Code: "Create a scene for this part of the video" 3. Claude Code reads my brand, generates the HyperFrames scene, renders it to MP4 4. Drag the MP4 into Descript, drop it on the matching line of the transcript 5. Done. 3-5 minutes per scene. The unlock is the brand style guide. Once Claude has your colors, fonts, and reusable components, every scene inherits your look automatically. Bonus — you can take a Claude Design export (.zip), hand it to Claude Code, and it'll convert the HTML into a HyperFrames video you can render and edit. I built a GitHub repo with all the skills pre-loaded. Non-developers can clone it, open Claude Code, and be rendering scenes in under 10 minutes. Full walkthrough (20 min video) below Repo (skills + brand template + music-from-transcript plugin): github.com/JJenglert1/vid… Bookmark this if you make videos. The brand-style-guide pattern alone will save you hours every week. If you're a creator or operator using AI for content — share this with someone who's still living in After Effects.

@rileybrown Great, thanks for sharing! Loss of control, jobs/skills and meaning seem to be the outliers

Why do people hate AI. Here's a report by codex after analyzing 20,000 comments on anti-ai youtube videos why-do-people-hate-ai.vercel.app

@boardyai give your agents a home superceo.ai

Drop your startup ↓ Let's drive some traffic

@garrytan The main issues I'm seeing now is when you have too many skills, it's hard to actually keep track. Maybe some way to visualize, understand most used, most recent. It feels a bit like skill bloat These are my current challenges

GBrain Skillpacks are my attempt at this

Dynamic skills are one of the coolest and most powerful parts of the new way to make personal AI work Just in time and markdown is code, and the agent can just change it when you discover new cases to handle Just in time personal software is the most powerful idea of 2026

if you're curious for agent orchestration techniques - try this out its free its fast its local and its the future

>> x but its a newspaper

@kimmonismus he'll probably confirm it after io

@techguyver you think so?

If that really was AI-generated, then it caught me completely off guard. Anyway, Gemini today

@balajis The understanding is that they will keep on getting better and better and the bottleneck will be in the management delegation observation, etc In order to be able to coordinate between them and get the best bang for work

@balajis precisely - im trying to solve this superceo.ai

Every AI agent ultimately has a human principal.

live claude from london youtube.com/watch?v=AgQ4cw…

@olivercameron @odysseyml @grok what's the difference between this and Genie?

Introducing Starchild-1 from @odysseyml, the first ever real-time multimodal world model. This a model that can generate interactive simulations of the world that you can—for the first time ever—hear. Starchild-1 represents a big step towards a general-purpose world simulator.

just checking in on /goal gta6 ... x.com/gregpr07/statu…

hyperframes.dev vs remotion.dev - which one is less code do you think?

@olivercameron if you die in the odyssey agora-1 do you die in real life?

Just pwned some newbs on Agora-1.

real time youtube

anthropic should buy decart and add real time video to claude rn

@thatguybg not enough demo of what the actual product is / how it works IMO

pretty good research-oriented launch video - great set design - great camera quality - music is fantastic (notice how it has some 007 vibes when you see the game. plus there's a cool sonic logo at the end) but - not a great scroll stopper - cuts are too long - need subtitles, text, and more imagery to make sure people are following - would put the actual demo further up - would also have the demo video more clearly show two people in the same world (wasn't clear) - would explain how it works (this is a technical breakthrough after all) - would lean harder into the nostalgia (make the room more 90s, maybe some quick cuts of super 90s items as the scroll stopper) - would have focused the narration on what makes multiplayer games so great (LAN parties, shit talking, etc) and then say world models can't create this experience (then show the visuals of the multiplayer vanish)... until today (then introduce the product) - add the domain to the CTA very cool product tho. congrats on the launch.

@Miguel07Code @HyperFrames_ EXPORT TIME.. needs to be much faster

We're planning our next updates and want to hear from our power users. For people using @HyperFrames_ every day: what is the ONE thing you would most want to see added or improved inside the Studio or CLI? It can be anything

So Veo4 is dropping tomorrow>