⠋ building cool stuff ⠙ 23 ┃product engineer @HeyGen based in Toronto ┃ Built @editfa_st ┃Building @HyperFrames_ by HeyGen

🇪🇸/🇨🇦/🇺🇸
Joined August 2023
just a happy boy from a small town in Spain, here in SF thanks @HeyGen_Official @joshua_xu_ @liu8in for making it possible ❤️
11
1
112
18,394
Miguel Ángel retweeted
This is a great take. I want to recommend a video on this topic too. This new video from @AliAbdaal is the clearest picture I've seen of where agentic editing is today. Ali spent a day learning AI editing end-to-end and tested it against his own editor, and ran HyperFrames vs Remotion head-to-head. If you want a real sense of where we are with visual examples, I highly recommend watching this: youtube.com/watch?v=C0jOKDJt… Clip from Boss Battle attached below (42:18–43:13) 👇
A few thoughts on agentic video editing I’ve had over the last few days: 1. 99% of ads should be edited agentically now. If your editors are still editing in the timeline, they’re falling behind. I got a message from my senior VE saying that he’s putting out 5x edits/day now at the same quality he was before. 2. The conversation with video editors will be uncomfortable because the timeline is all they’ve ever known. Some will be hesitant and some will be fearful for their job. I think the best way to address this is head on. The tech is inevitable, but having taste is still going to be incredibly valuable to train and give feedback to agents. Those who have this will become more valuable, those who don’t will struggle. 3. Opus 5.5 can natively edit all of your ads without needing any MCPs or plugins. I’ve tried the alternatives and couldn’t find anything that was significantly better than doing everything inside of Claude. 4. Have your senior editor(s) build skills for each style of edit (e.g. mashups, UGC, AI animations…). You can build these by feeding 4-5 inspo edits to Claude and tell it to make a skill out of it. I prefer building lots of mini-skills to one big video editing skill, so that the context stays as relevant as possible. 5. Once you have a base skill (e.g. ugly ads edits), the best way to train it is through feedback loops. Have the skill re-edit the last 25 ads each senior edited then put them in an artifact, and have the senior VE give feedback on each. Keep doing this until the skill is refined and it understands what a good edit is. 6. If you do this, there’s no reason why you shouldn’t be able to make edits that need little/no feedback. Most of ours are approved after v1 or v2, sometimes v3. 7. Only A-player editors should be training the skills. 8. Re adoption in the team, the AI champion builds the v1. Then get out of the way. I’m not the best editor on my team, so my job is to build the harness that lets the best editors train the skills, not build the skills myself. 9. If you want to supercharge this process, have your top editors record their screen as they edit. Turn on Gmeet or loom and get them to narrate the reasoning behind their process. E.g. why they chose this cut, pacing or b-roll clip…this is all context that gets fed into your skills. 10. It takes time to build, train and refine these skills. You have to go through the dip to get out the other side. Budget time in for senior VEs to work on this - otherwise you’ll end up with skills that put out subpar edits and don’t save you much/any time. 11. Operate under the assumption that this is the worst video editing is ever going to be. Opus 5.5 can do most of our editing today…what will Opus 6/Fable 6 be able to do? The editing skills you build are only going to become more valuable as the tech evolves. I still don’t think people realise how big video editing being unblocked is. Things that I thought were 3-6 months away are now on the table. Will continue to share more as I learn. CRAZY, crazy times.
8
5
84
5,495
Miguel Ángel retweeted
the great @AliAbdaal trying @HyperFrames_ for the first time!! I’m beyond excited TLDR: HyperFrames won out amongst Davinci, Remotion for agentic video editing by a first time novice (we didn’t pay him but I’d love a paid partnership!) youtu.be/C0jOKDJtK9s?is=XPMO…
3
3
1
45
3,775
it's like agentic coding, if you code manually you'll be left behind, now it's the same time for video editors or marketers, all will be code soon so become an early adopter as soon as possible
great to see so much energy behind agentic video editing i'm sorry, but forget MCPs for Davinci / After Effects. people won't be installing these anymore. most people don't ever need to. @HyperFrames_ was architected for this new era of video production the entire stack should be re-imagined just imagine if Disney / Pixar didn't move from hand-drawn frames to CGI this transformation is happening RIGHT NOW for video editing and it's centered around ai agents be agent-native, or get left behind
1
9
375
it almost feels like a dream sometimes
Replying to @HyperFrames_
@HyperFrames_ in its first 90 days: 1.3M renders Today: • 15.8M+ local renders • 1.36M users/agents • ~427K local renders/day • ~74K GitHub stars Since every agent can write HTML it can also make a video This data was from my AI Engineer talk back in July
7
367
first time someone tried to unify UI standards, this is a frontend revolution 🚬
Replying to @shuding
What does this mean for the future of UI? UI code, the rendering engine and production metrics will merge into one loop. Code will see inside the engine, the way games have for decades, and metrics will shape the UI directly instead of sitting in a dashboard. And formal methods can bring code’s standards to UI. Instead of comparing screenshots, CI could prove a change never causes a layout jump on any device, across infinitely many screen sizes, the way a type checker proves code is sound. All demos: calculus-of-interfaces.verce… shu @vercel labs
7
327
pure dopamine just entered my cortex
UI and math time! UI = f(props) is the most famous line in React. But that f is JavaScript, not math. Inspired by @_chenglou’s Handwired project, I compiled a <Dashboard/> component into a real math function, and asked what becomes possible. calculus-of-interfaces.verce…
8
418
Miguel Ángel retweeted
Great writeup on agentic video which we've been working on quite a bit with @HyperFrames_ We've been able to democratize video creation internally because of agentic editing and it's how we are able to create launch videos every day without needing a phd in after effects or premiere pro
A few thoughts on agentic video editing I’ve had over the last few days: 1. 99% of ads should be edited agentically now. If your editors are still editing in the timeline, they’re falling behind. I got a message from my senior VE saying that he’s putting out 5x edits/day now at the same quality he was before. 2. The conversation with video editors will be uncomfortable because the timeline is all they’ve ever known. Some will be hesitant and some will be fearful for their job. I think the best way to address this is head on. The tech is inevitable, but having taste is still going to be incredibly valuable to train and give feedback to agents. Those who have this will become more valuable, those who don’t will struggle. 3. Opus 5.5 can natively edit all of your ads without needing any MCPs or plugins. I’ve tried the alternatives and couldn’t find anything that was significantly better than doing everything inside of Claude. 4. Have your senior editor(s) build skills for each style of edit (e.g. mashups, UGC, AI animations…). You can build these by feeding 4-5 inspo edits to Claude and tell it to make a skill out of it. I prefer building lots of mini-skills to one big video editing skill, so that the context stays as relevant as possible. 5. Once you have a base skill (e.g. ugly ads edits), the best way to train it is through feedback loops. Have the skill re-edit the last 25 ads each senior edited then put them in an artifact, and have the senior VE give feedback on each. Keep doing this until the skill is refined and it understands what a good edit is. 6. If you do this, there’s no reason why you shouldn’t be able to make edits that need little/no feedback. Most of ours are approved after v1 or v2, sometimes v3. 7. Only A-player editors should be training the skills. 8. Re adoption in the team, the AI champion builds the v1. Then get out of the way. I’m not the best editor on my team, so my job is to build the harness that lets the best editors train the skills, not build the skills myself. 9. If you want to supercharge this process, have your top editors record their screen as they edit. Turn on Gmeet or loom and get them to narrate the reasoning behind their process. E.g. why they chose this cut, pacing or b-roll clip…this is all context that gets fed into your skills. 10. It takes time to build, train and refine these skills. You have to go through the dip to get out the other side. Budget time in for senior VEs to work on this - otherwise you’ll end up with skills that put out subpar edits and don’t save you much/any time. 11. Operate under the assumption that this is the worst video editing is ever going to be. Opus 5.5 can do most of our editing today…what will Opus 6/Fable 6 be able to do? The editing skills you build are only going to become more valuable as the tech evolves. I still don’t think people realise how big video editing being unblocked is. Things that I thought were 3-6 months away are now on the table. Will continue to share more as I learn. CRAZY, crazy times.
1
14
578
one of the best creative minds I know, crazy
One crayon drawing, four ways to move. 🖍 Made with HeyGen Video 1 from text alone: no reference image, no editing. Each clip is one prompt, 8 s, vertical 1080p, with the sound.
3
9
429
Miguel Ángel retweeted
everyone's posting videos made with Opus 5.5, but most don't show you how Pit Crew Academy is live in HyperFrames Studio we turned months of making videos and templates into lessons from beginner to pro anyone can create pro videos now get started ↓
20
15
5
283
12,823
you can just farm millions of views with HyperFrames 🤯
Gokilll. Video kedua tembus 1 juta views di Tiktok 😁🔥 Claude Pro + Hyperframe + Elevenlabs 🔥
1
351
Miguel Ángel retweeted
"over 1,000 medieval scribes have joined the Association for Human Manuscripts, pledging to never use the printing press or work with Gutenberg 654 have gone even further, promising to never read a printed book"
Wow, over 1,000 mathematicians have now joined the Association for Human Mathematics (AHM), committing to: > NOT publish AI generated math papers > NOT work with frontier labs > 654 of them went even further to NOT even use AI in their research, at all
95
247
17
3,016
124,488
Miguel Ángel retweeted
SWE-bench tells you which model writes working code Code2Video tells you which one makes a video people want to watch it's now a standalone leaderboard on @ArtificialAnlys 27 models, judged head to head on engagement, prompt intent, composition, temporal consistency and craft Claude Opus 5.5 still leads Check out their article here ↓
Introducing Code2Video-AA, our independent implementation of HeyGen’s Code2Video Bench, which evaluates how well models create product and brand marketing videos in code Code2Video-AA tests models across 114 design briefs, tasking them with turning each product or brand marketing brief into a @HyperFrames_ HTML composition, which we render to video. Model outputs are evaluated through pairwise comparisons with other model outputs across five axes: Engagement, Prompt Intent, Composition, Temporal Consistency, and Craft. We use the outcomes of these comparisons to calculate an Elo rating for each axis, which are then averaged to produce the headline Code2Video-AA Elo. Code2Video-AA was built in partnership with @HeyGen. Claude Opus 5.5 (max with fallback, 1536) leads Code2Video-AA by 93 points, but costs $3.08 per task, ~10x more than GPT-6.1 Sol (max, 1369), which trails by 167 points. Key findings: ➤ Claude Opus 5.5 leads on all five judge axes: Models are judged across 5 axes: Engagement, Prompt Intent, Composition, Temporal Consistency, and Craft. Claude Sonnet 5.5 (max with fallback, 1443) and GPT-6 Astra (max, 1427) are statistically tied for second in overall score ➤ Cost per task varies more than 300x, from $0.01 to $3.89: GPT-6.1 Sol (max), fourth, has a Cost per Task of $0.31, about 90% lower than Claude Opus 5.5 (max with fallback) at $3.08 ➤ Open weights models trail by at least 483 points: DeepSeek V4.1 Flash (max, 1053), MiMo-V2.6-Flash (1052) and MiMo-V2.6-Pro (1052) are the top open weights models, at $0.01 to $0.08 per task Code2Video-AA details: ➤ Models are tested on a single response without tools. We render it with HyperFrames, with no network access ➤ A judge (Gemini 4 Argon, high) compares pair of videos across five axes: engagement, prompt intent, composition, temporal consistency and craft, with the final score being calculated from a combination of each individual axis Elo ➤ Over 35,000 verdicts rank 27 models by Elo, with 95% confidence intervals More results, example videos and how Code2Video-AA works follow in the thread below
7
8
97
5,261
LFGGG
Introducing Code2Video-AA, our independent implementation of HeyGen’s Code2Video Bench, which evaluates how well models create product and brand marketing videos in code Code2Video-AA tests models across 114 design briefs, tasking them with turning each product or brand marketing brief into a @HyperFrames_ HTML composition, which we render to video. Model outputs are evaluated through pairwise comparisons with other model outputs across five axes: Engagement, Prompt Intent, Composition, Temporal Consistency, and Craft. We use the outcomes of these comparisons to calculate an Elo rating for each axis, which are then averaged to produce the headline Code2Video-AA Elo. Code2Video-AA was built in partnership with @HeyGen. Claude Opus 5.5 (max with fallback, 1536) leads Code2Video-AA by 93 points, but costs $3.08 per task, ~10x more than GPT-6.1 Sol (max, 1369), which trails by 167 points. Key findings: ➤ Claude Opus 5.5 leads on all five judge axes: Models are judged across 5 axes: Engagement, Prompt Intent, Composition, Temporal Consistency, and Craft. Claude Sonnet 5.5 (max with fallback, 1443) and GPT-6 Astra (max, 1427) are statistically tied for second in overall score ➤ Cost per task varies more than 300x, from $0.01 to $3.89: GPT-6.1 Sol (max), fourth, has a Cost per Task of $0.31, about 90% lower than Claude Opus 5.5 (max with fallback) at $3.08 ➤ Open weights models trail by at least 483 points: DeepSeek V4.1 Flash (max, 1053), MiMo-V2.6-Flash (1052) and MiMo-V2.6-Pro (1052) are the top open weights models, at $0.01 to $0.08 per task Code2Video-AA details: ➤ Models are tested on a single response without tools. We render it with HyperFrames, with no network access ➤ A judge (Gemini 4 Argon, high) compares pair of videos across five axes: engagement, prompt intent, composition, temporal consistency and craft, with the final score being calculated from a combination of each individual axis Elo ➤ Over 35,000 verdicts rank 27 models by Elo, with 95% confidence intervals More results, example videos and how Code2Video-AA works follow in the thread below
1
7
494
meme made with @HyperFrames_, you can just create great memes with it and copy any meme too inside the desktop app btw
claude usage was temporarily blocked today and i felt my stomach drop to my toes
2
6
521
Miguel Ángel retweeted
Improved this video with HyperFrames studio and one prompt give your features the launch they deserve with @HyperFrames_
Link balance is live in Instinct, built with @Stripe and @link. Add money, set a per-purchase limit, and your Instinct can make purchases on your behalf within those limits. Rolling out across the US starting today (NY coming soon). Ask your Instinct to set it up.
2
4
13
715
fact
you've asked for this more than anything else HyperFrames Studio is live on Windows get started ↓
1
1
12
448
FINALLY WINDOWS APP FOR HYPERFRAMES DESKTOP APP YESSSS ping me for any issue 🫡
you've asked for this more than anything else HyperFrames Studio is live on Windows get started ↓
5
1
20
851
the best way to understand the S1 filing from @AnthropicAI using @HyperFrames_ Studio!
I'm not reading 300 pages, so I let Opus 5.5 create this video in @HyperFrames_ Studio to explain the 10 most interesting pieces of the S1 filing
1
1
15
1,266
Miguel Ángel retweeted
Kurzgesagt has 25M subs. Millions of views on EVERY single video 🤯 nobody copies them for a reason: one video takes 1,200 hours and a studio of 50+ animators. we rebuilt their format with Opus 5.5 + @HyperFrames_ Studio. 100% code. a full 11-minute explainer. made in ~2 hours. under $50. want the template? we’re open-sourcing it for free 👇
253
60
62
1,138
342,308