HyperFrames Studio is the easiest on-ramp to AI video editing I've ever seen. It's like what Canva did for democratizing design. In 24 hours, I made all of this without opening Premiere or Final Cut: - a 25-min podcast, fully edited with an intro, captions, and archival footage - a spreadsheet turned into a flashy video - tons of slick launch videos for apps that may or may not exist I was just drawing on the screen, typing in a text box, and telling AI what I want. It's the new (free!) editor from @HeyGen. @HyperFrames_ used to be kind of a nerd tool. You prompted it in Claude Code, sat back, and hoped it came back clean. Now there's a timeline, a chat box, and a pen: circle what's off, say what you want, and it fixes it. I don't think I could ever go back to writing out timestamps. I made a 15-min walkthrough, front to back. Here's what's inside: (1) setup: what you need (spoiler: a Claude, Codex, or Grok sub + a Mac or Linux machine) (2) the tour: inspirations, model picker, and the draw-to-edit trick (3) 6 builds from real files: a CSV, a voice memo, a Luma link, a 25-min podcast, a vibe, and a selfie video (4) the good, the bad, and the ugly The honest part: give it one sentence and you'll get ✨slop✨. It's also very much a day-one app (ghost frames, some clunky timeline navigation), but updates are shipping multiple times per day. Who it's for: - total beginners who've never opened an editor - accountants and marketers sitting on spreadsheets, decks, and webinar pages - anyone burning tokens regenerating clips in Higgsfield - pro editors who want to begin delegating mundane tasks to AI What would you make first? watch here:

10 things AI video editing did this week that used to eat hours of my life while creating content: 1. cut 34 min of raw footage + screen share down to a 16:00 video 2. synced my multicam clips, perfectly timed and formatted 3. matched the color grade between my iPhone and my DSLR footage 4. iterated motion graphics for a whole video in Higgsfield 5. turned an excel spreadsheet into a motion graphics presentation 6. found 10 potential shorts in a podcast... then chopped them up 7. pulled still frames for my thumbnail and exported the best ones 8. grabbed archival footage + memes from across the web. didn't download a thing 9. found music and sound effects and timed them to the cut 10. made me ask IT for more usage credits. FOUR separate times a few of these came from @HyperFrames_ Studio, the editor @HeyGen dropped this week (that's it in the vid). my full review + tutorial is coming soon 👀 fellow creators: what's your #11#?

claude is HEAVILY pushing artifacts right now. they cost 50% less usage until oct 15 (pro, max, and team plans). if you're not building with them yet, this is the week to start. i made a 12-min walkthrough that takes you from zero to pro. no coding experience required. here's what's inside: 1. docs with live charts. my weekly social memo has interactive charts i asked for out loud 2. design systems. send claude a few pinterest screenshots (or your website URL) once, and everything after comes out on brand. i used it to make a y2k pitch deck for bringing back the ipod lol 3. edit by commenting. highlight any part of an artifact, leave a comment, and claude changes it. i added a whole new "starred" tab to my study app with one comment 4. live dashboards. plug in a connector like hubspot and ask it "who should i call first today?" 5. multiplayer boards. my team is using one right now to plan our new video studio. paste in an image and claude sorts it for you 6. team voting. i built a packaging lab where my team votes on youtube thumbnails, so the decision doesn't get lost in slack sleeper feature: when someone uses the claude features inside an artifact you shared, it runs on THEIR usage, not yours. share it with the whole internet without giving away your claude for free homework: pick one thing you do every week (a report, a deck, a tracker) and turn it into an artifact before oct 15. what are you building first? watch here:

In one day, I went from complete fucking noob to... a Jev power user? (Read this, and you can too!) I've been playing with Jev, a new AI model from @typesafeai. I'm not a developer, so I wanted to find out what I could actually build with it. I made four increasingly crafty/interesting demos: An email sorter 2,000 test emails sorted into buckets in 4.4 seconds, for about 4 cents. It flags uncertain cases for a human to review. A customer-review playground Would this person buy again? What should we improve? How did they feel about the product? Ask all three and get answers your app can use. “Should I send this Message?” Got anger issues? Give it your draft Slack or email... whether you're about to rage quit, or saying something nice. It picks send now, soften first, sleep on it, or say it in person. “Am I bombing?” A pitch-coach experiment. The browser uses Face API to turn camera and voice cues into numbers; Jev uses those to suggest feedback. I simulated nervous and confident pitches to show the feedback changing. Each one uses the same basic idea: give Jev the situation and the possible answers. It picks an answer, tells the app how sure it is, and the app uses that result. You can start with one judgment you're tired of making over and over! Here's my Jev Test™ for new and existing projects: (1) Do I keep asking the same question? (2) Can I name the possible answers? (3) Would deciding faster or more often actually help? If something in your work passes all three, that's a place to start. Full 10-minute walkthrough attached, including when I'd still use Claude or ChatGPT. Watch on YouTube: What decision at work would you build one of these for? (Shoutout to @tenex_labs' finest -- @seejayhess and @_raghavdixit_ -- for the knowledge you imparted for this one!!)

I’m happy to announce that AI is finally coming for my job. This intro you see was made with GPT-6 Astra. I gave Codex my raw footage, my script, and access to Final Cut. I described the visual direction with screenshots of references and natural language, and viola - beautiful results. I still want to bring my own perspectives, come up with fun ideas to explore, and decide what deserves to be on screen. But the exporting, dragging, dropping, and repetitive cleanup? Please take it!! Creators: what part of the process would you happily hand off? Watch the full video here:

My brother-in-law landed a job interview for two reasons: 1. He used AI to optimize his resume keywords for the ATS scanner 2. He dropped a bullet under Skills that read: "bicycle repair, eccentric ideating, frolicking amongst foliage and critters, and patriotism" Guess which one they asked him about. AI has a personality, but it’s just the average of everything it knows, and everybody's has the same one. Your quirks, your references, the weird asides you put in in parentheses — your ✨authenticity✨ — that’s the last remaining “moat” to stand out in anything you produce. That's one of 5 things I learned making this video essay. I spent a day yapping with my team at Tenex (people who are hired FOR their AI skills how they avoid making slop with it) to try and figure out: Why do people drift from using AI for grunt work to completely outsourcing their thinking to it? The point here isn't as simple as "AI Bad" -- it's about how to put your thinking cap back on! Tap in and tell me if there's a pointer I missed.