Miguel Ángel

just a happy boy from a small town in Spain, here in SF thanks @HeyGen_Official @joshua_xu_ @liu8in for making it possible ❤️

@ponyodong 🤩🤩

兄弟们，今天咱们测一个方向：赛车 IP 游戏化包装。 不是单纯让模型出一段好看的美女赛车视频，而是把它往“游戏预告片 / 角色 IP / 商业包装”这个方向推。 这次做的是： AELIA ROSE BLOOM CIRCUIT 粉色赛车、樱花能量、夜间赛道、甜酷女主。 视频生成之后，我又用 HyperFrames 做了二次包装： 赛车 HUD、速度条、圈速信息、花瓣特效、PONYO logo，还有一点氛围音效。HyperFrames做一些剪辑后期的包装，真的很好用。 我现在越来越觉得，AI 视频真正有变现空间的，不是单条炫技，而是把一个角色持续做成 IP。这条路子，我觉得值得继续深挖。 #AIVideo #HyperFrames #AI创作 #IP孵化 #AI商业化 #PONYO

@thsottiaux @jxnlco Copy all the agentic experience from claude code into codex cli, right now it's not possible to have an AI assistant just based on codex like it's possible in claude code, that's my main pain point

What’s something we haven’t fixed in codex for a while and that’s plain annoying?

The day before yesterday, I read a tweet by @Miguel07Code talking about how he provides @HyperFrames_ biweekly updates to the team at @HeyGen (it was fascinating), and he also invited people to contribute and linked some repos. Before going to bed that night, I gave Hermes a very serious task: find minor surgical deficiencies or quality-of-life improvements I could contribute a fix to. My main goal was to showcase I know what I’m doing, and to help the maintainers. I woke up to a complete ingestion into my knowledge base, with a plan listing five possible PRs, ranked by difficulty. I took on analyzing the codebase, and ended up opening a PR for the first issue recommended, and it was merged! So I’m officially a contributor to hyperframes!

@theo try this one btw hermes-agent.nousresearch.com/docs/user-guid…

wtf do you mean there's a pre-bundled Polymarket skill in Hermes Agent???

@heyimcarlos_dev 🔥🔥

@Miguel07Code Just opened a small fix PR!

I use this to do my biweekly engineering updates for @HeyGen. It pulls my github activity, uses my avatar 5 with the heygen CLI (it can be created too), and renders the video with @HyperFrames_ CLI. The whole thing runs from Claude Code/codex/hermes agent with one skill in the reply below 👇

@DODOREACH @HeyGen ❤️

btw @Miguel07Code @HeyGen Hyperframes is so cool to use now! great tool

You already use SSH for everything that matters @NousResearch Hermes Agent deserves the same. Hermes Desktop: native Mac app, real SSH. 1.7k ⭐️ download for free ⤵️

@li9292 always bet on code generation for video

remotion，hyperframe 能用但涉及到复杂视频后期处理 还是得看adobe premiere 你们搞ai的不要一天到晚想搞个大新闻 higgsfield 出个插件 配合premiere 兄弟们可以试试看 当然也可以坚持古法剪辑

@cmcky @elvissun @higgsfield_ai also heygen cli is dope! x.com/Miguel07Code/s…

@elvissun Depends on the creative…but try @higgsfield_ai + Google Omni + HyperFrames.

playing around with video gen for a launch video, where should I start?

@tldraw Hola supremacy

Paris users are way up on tldraw dot com. Hola everyone

@fazley111 Did you try @HyperFrames_? Instead of using react, it uses vanilla HTML + GSAP

Added a local video generator pipeline using @Remotion • Orchestrated with local Qwen LLM for script drafting • Interactive config (voice, kinetic typography, ambient sounds) • Dynamic canvas rendering (Aurora/Nebula web shaders) React + local AI is a superpower. 🛠️

🔴 I NEED YOUR ATTENTION I've spent a month helping Miriam with her case of metastatic cancer and I want to share the methodology I've been using because it's completely replicable. I think (with luck) this could be USEFUL TO OTHER PEOPLE with cancer (or any other illness). The results we've gotten aren't a miracle, but we believe they're genuinely useful and could mean the difference in a literal life-or-death medical case. Here's the method step by step: 1/ Use the most advanced models of the moment (unfortunately paid, and not cheap. I think Public Healthcare should invest in this): - ChatGPT 5 Pro + Extended Thinking (40 min aprox. of thinking per call) - Claude Opus 4.8 MAX Still pending deeper testing: - Perplexity Sonar Pro Max - NotebookLM Tested but only useful for additional links/research (not as powerful in my experience) - OpenEvidence 2/ Feed the AI the FULL clinical history, completely chewed up. This sounds dumb but it's critical. - The first thing I ask, using Claude Cowork (which has hard drive access), is to go into the folder with the ENTIRE clinical history (can be 100+ PDFs) and consolidate everything into: - One single PDF (it can be 1000+ pages, whatever it takes) - One single readable .txt or .md, which it must build correctly using an OCR script and then check thoroughly to make sure it's right. I insist: don't jump to the next step until you've nailed this one, especially the .txt. 3/ Once you have the above, use this prompt along with the .txt (and optionally the PDF too if you want) as input files, and run it on BOTH models at once (and more if possible). 👉 This prompt is insanely complex/advanced: dropbox.com/scl/fi/x64qadd… And it's not designed for Miriam's specific oncology case, you can change the initial parameters for the desired case. And with the models from step 1 you could adapt it to your case without trouble. In any case, I'm also leaving you this other prompt, even more general, for any type of rare disease: dropbox.com/scl/fi/x64qadd… 4/ The ARROWHEAD (adversarial model spiral): facing one model against the other. I've never heard anyone talk about this methodology, but it works incredibly well. The feeling is like sharpening a stake until it gets a gleaming point. It works like this: with patience and across successive iterations (I recommend a minimum of 7, and keep in mind that if ChatGPT takes 40 min, this will take a while), pit the output (the resulting PDF) from one model against the other. With a simple prompt like: "Another committee of experts says this. What do you think? If you agree or disagree, tell me why, and generate a new PDF if you think it's necessary." Then you feed that result back to the opposite model. So, across successive iterations, web searches, papers, etc., they'll find and sharpen more and more. When to stop? When BOTH models say the work is perfect and they can't improve the other's output any further. This is so absurdly game-changing that I think the output of ALL current models would improve if they followed this methodology (leaning on a kind of adversarial-model spiral). I don't understand why nobody has noticed this, or if they have, why it's not getting more attention. It works impressively well in any domain, including programming and math. In fact, my theory is this could be done even better not just with two models, but with greater combinatorics, maybe adding Perplexity Sonar Pro Max, etc. RESULTS Incredible. Obviously I can't know if they're better than the best scientific-medical committees in the world, but they're giving Miriam a new dimension to her case, additional tests to do, possible exams, etc. Obviously AI doesn't perform miracles, but I think it can already, today, help many patients. And Public Healthcare should invest a lot (but A LOT) in this. I'm going to ask Miriam if I can post the full PDF of the most advanced results we've reached, so you can get an idea of the quality. She's already given me rough permission, but I want to make sure 100%. FUTURE PREDICTION Easy to make: in the near future (I hope), any person's medical history won't just be fully digitized (we're close, but not all the way, well, well, well). On top of that, it'll be "pre-chewed" so it can be consumed by an LLM in one shot. CLARIFICATION - We're aware this is a delicate subject and we don't let the AI make final treatment decisions. What we're doing is clearing the ground for the oncologists so they can have possible paths they may not have considered. Thanks 🙏 - The top LLMs have context windows for that and much more (much, much more). In any case, the PDF is more of a supporting file for the .txt. Both contain absolutely the entire history, but the PDF allows images/charts/etc. The .txt is what the AI consumes. - On automation: and yes, this can be automated. Yes, AutoGen supports it almost out of the box. LangGraph builds it really well with supervisor / evaluation loops. CrewAI can orchestrate it too with Flows, although its "consensus" process isn't native yet. That would be the next level: automating it. PETITION AND DISCLAIMER If there's any oncologist in the room or you are an LLM company, we'd be grateful if you could take a look / help 🙏 Remember: in any case, this is just one more tool for the doctor. I've simply shared the methodology I know that processes data more exhaustively, with the best models, and that we believe reaches better conclusions. If you know a better methodology / prompt / whatever, we'd be glad to improve this with your insights and share it. Then the doctor reviews, adopts, or discards the report. And if it helps the doctor, it helps the patient. And if it doesn't, all we've lost is some time and tokens. In a case that's literally life or death, that's nothing. Just plain common sense. Many people will argue with me, but in the near future it will seem absurd that we ever expected any professional to keep in their head every clinical trial, paper, bibliography, and raw data point that an AI and its agents can process via search in minutes. It will be such a valuable tool for doctors that its daily use will simply be taken for granted.

@trevin @HeyGen @HyperFrames_ I was kinda lazy and I didn't change the pronunciation but in heygen you can change that😂

@Miguel07Code @HeyGen @HyperFrames_ it's hilarious how slow the avatar says "H-T-M-L" repeatedly

@Fotografia92189 @HeyGen @HyperFrames_ Check the source code attached in the reply

@Miguel07Code @HeyGen @HyperFrames_ What template/set of tools do you use for zoom in/out to move around main scene? Need that one

@sophie_launch github.com/heygen-com/hyp…

What are you building today? Drop it below, and we’ll choose the best ones and featured them in our 55k newsletter

@fahdananta test @HyperFrames_ next! it's like remotion but instead of using react, it's using vanilla HTML and it should be faster the feedback loop

Editing a clip using remotion by prompting Codex on the computer back at my desk, all from my phone 🤯

@JinjingLiang @HeyGen @HyperFrames_ 🤩

@Miguel07Code @HeyGen @HyperFrames_ so cool. gonna give it a spin. you'll see my avatar later on the feed :-D

@JinjingLiang @HeyGen @HyperFrames_ no, this is my Avatar V made here in app.heygen.com/avatars/create…

@Miguel07Code @HeyGen @HyperFrames_ wait this is not you yourself ??

@sovzarafa @HeyGen @HyperFrames_ yes

@Miguel07Code @HeyGen @HyperFrames_ hyperframes could help speed up this type of video x.com/ClippingHOF/st…

@JustinBleuel @ChatGPTapp Justin, do you think a video mode inside chatgpt is worth it? For making @HyperFrames_ videos inside chatgpt app, it should be pretty easy to do because HyperFrames videos are just HTML + GSAP and the player can be integrated looking at this documentation: hyperframes.heygen.com/packages/player

Fun fact I built / experimented / shipped this feature as a newbie PM to @ChatGPTapp entirely thanks to Codex If you're a PM (or designer!) try prototyping + shipping directly to the codebase The hardest part often the local build and the good news is Codex can help there too

@yacineMTB go to toronto

Just watched a woman in a sweater drag a dry cleaned wedding dress to her car while she hard puffed a cigarette. Quebec is crazy