Загрузка видео...

Не удалось загрузить видео

На главную

The idea isn't "make original content." It's find what's already working, hand it to GPT-6 Astra to reverse-engineer, then let Postiz handle the boring part. This setup is pulling +26.4M views a week! > The research: TikTok's own like-filters show what's repeatably viral, not what got lucky once >...

neil_xbt's profile picture

NeilXbt

16,815 subscribers

13,798 просмотров • 11 дней назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 8

Фото профиля Pedro Pérez
Pedro Pérez11 дней назад

easier than it looks

Фото профиля PronosFoot Data
PronosFoot Data11 дней назад

The 3k cutoff is ruthless but smart. This is how AI becomes a production engine.

Фото профиля angelikita
angelikita11 дней назад

GPT + Postiz is a crazy combo

Фото профиля Ｃｒｙｐｔｏ Ｄｅｎｉｚ
Ｃｒｙｐｔｏ Ｄｅｎｉｚ11 дней назад

Reverse-engineering winners is the cheat code.

Фото профиля Thalapathy_vj_shruthi💞
Thalapathy_vj_shruthi💞11 дней назад

This is the real AI content flywheel 🔥

Фото профиля Ryan Mercery
Ryan Mercery11 дней назад

26.4M views a week is insane 👀

Фото профиля Brjan | AI Builder
Brjan | AI Builder10 дней назад

If you're just recycling what’s already viral, originality might take a hit

Фото профиля Nahid
Nahid10 дней назад

+26.4M views a week is insane for AI

Похожие видео

This 24-minute tutorial shows you exactly how to create AI UGC with GPT-6 Astra from scratch but making the UGC is the easy part the real advantage is turning it into a system that can consistently find what works and scale it that's exactly what this article breaks down: → find UGC formats already going viral → use Astra to reverse-engineer why they work → generate new variations from those patterns → batch-create a full week of content → let your agent + Postiz organize, schedule and distribute it → track the winners and use them to build the next batch one viral format becomes dozens of pieces of content and the whole loop starts again watch the tutorial below, then read the article for the complete workflow👇
11:59

This 24-minute tutorial shows you exactly how to create AI UGC with GPT-6 Astra from scratch but making the UGC is the easy part the real advantage is turning it into a system that can consistently find what works and scale it that's exactly what this article breaks down: → find UGC formats already going viral → use Astra to reverse-engineer why they work → generate new variations from those patterns → batch-create a full week of content → let your agent + Postiz organize, schedule and distribute it → track the winners and use them to build the next batch one viral format becomes dozens of pieces of content and the whole loop starts again watch the tutorial below, then read the article for the complete workflow👇

Nico

17,679 просмотров • 11 дней назад

The interesting part isn't just generating a product. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. It's going from a draft → real-looking product → product page in one continuous workflow. I started with a simple product concept in Dreamina. Then GPT-6 Astra interpreted the draft, built out the actual product, and used it to create the final product detail page. Dreamina's pricing also makes it practical to generate a bunch of early concepts instead of overthinking the first one. This workflow is definitely worth experimenting with. #Dreamina #DreaminaPartner
0:28

The interesting part isn't just generating a product. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. It's going from a draft → real-looking product → product page in one continuous workflow. I started with a simple product concept in Dreamina. Then GPT-6 Astra interpreted the draft, built out the actual product, and used it to create the final product detail page. Dreamina's pricing also makes it practical to generate a bunch of early concepts instead of overthinking the first one. This workflow is definitely worth experimenting with. #Dreamina #DreaminaPartner

Md Riyazuddin

61,601 просмотров • 10 дней назад

OPENAI JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING GPT-6 ASTRA This is the most important prompting update for anyone using Astra. Bookmark this before your next build. Most people are still prompting Astra like GPT-5. That's the mistake. → audit your AGENTS.md — old instructions now fight the model → define autonomy explicitly — Astra pauses when you expect it to continue → cut skill descriptions to one line — too many skills and Astra sees none of them clearly → stop telling it to run tests — it does this automatically, repeating it causes overtesting → define stop conditions — Astra needs to know what "done" means Astra is at its best when you stop micromanaging and let it own the work. Read the full guide before writing your next prompt. GPT-6 Astra → Clean System Prompt → Autonomous Execution → Production-Ready Output → Ship faster
0:24

OPENAI JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING GPT-6 ASTRA This is the most important prompting update for anyone using Astra. Bookmark this before your next build. Most people are still prompting Astra like GPT-5. That's the mistake. → audit your AGENTS.md — old instructions now fight the model → define autonomy explicitly — Astra pauses when you expect it to continue → cut skill descriptions to one line — too many skills and Astra sees none of them clearly → stop telling it to run tests — it does this automatically, repeating it causes overtesting → define stop conditions — Astra needs to know what "done" means Astra is at its best when you stop micromanaging and let it own the work. Read the full guide before writing your next prompt. GPT-6 Astra → Clean System Prompt → Autonomous Execution → Production-Ready Output → Ship faster

Rahul

360,455 просмотров • 14 дней назад

most people use AI to make one video. that’s not the opportunity. the opportunity is building a system that produces an entire channel. instead of starting from a blank page, find Shorts already pulling millions of views. study what’s actually working characters, story structure, opening hook, pacing, visual style, the recurring format underneath it. then turn that into a repeatable workflow: find → analyze → extract → prompt → generate → publish → repeat. find a viral video in the niche you want. extract the storytelling structure not the video, the shape of it. use AI to turn that structure into an original concept and a detailed prompt. generate the scenes. edit them together, add narration, captions, music, sound. publish. do it again. the goal was never to reinvent the internet every morning. it’s recognizing what already holds attention, then building your own original variations inside that pattern. cute animated animals, simple emotional stories, funny situations, repeatable characters one proven format becomes dozens of original variations, not one video. document the process once, and AI handles the repetitive part of every version after. find proven demand → extract the structure → create an original variation → generate → publish → study results → improve → repeat. a single video might make you $5k . a format, run as a system across a whole channel, is what gets you into five-figure-a-month territory. one video is content. a system is a business.
0:48

most people use AI to make one video. that’s not the opportunity. the opportunity is building a system that produces an entire channel. instead of starting from a blank page, find Shorts already pulling millions of views. study what’s actually working characters, story structure, opening hook, pacing, visual style, the recurring format underneath it. then turn that into a repeatable workflow: find → analyze → extract → prompt → generate → publish → repeat. find a viral video in the niche you want. extract the storytelling structure not the video, the shape of it. use AI to turn that structure into an original concept and a detailed prompt. generate the scenes. edit them together, add narration, captions, music, sound. publish. do it again. the goal was never to reinvent the internet every morning. it’s recognizing what already holds attention, then building your own original variations inside that pattern. cute animated animals, simple emotional stories, funny situations, repeatable characters one proven format becomes dozens of original variations, not one video. document the process once, and AI handles the repetitive part of every version after. find proven demand → extract the structure → create an original variation → generate → publish → study results → improve → repeat. a single video might make you $5k . a format, run as a system across a whole channel, is what gets you into five-figure-a-month territory. one video is content. a system is a business.

RUX

19,207 просмотров • 1 месяц назад

OpenAI. said. this. publicly. their own engineers just proved one idea on themselves, in writing: stop telling AI what's wrong. hand it the whole broken thing and let it find out they gave GPT-6 Astra a slow test build of their own coding tool. one cause found, a memory bottleneck, one allocator swapped, every turn 25× faster this is GPT-6 Astra, the layer that fixes the cause instead of the symptom, $0 on top of the ChatGPT plan you already pay for: - open ChatGPT or Codex, pick GPT-6 Astra, hand it the whole thing: the folder, the file that takes a minute to open. it works in apps with no API and reads your screen - type one sentence: find the one cause, prove it, fix it, do not patch around it - leave the room. it asks without stopping, keeps working on what does not need your answer, waits only where the answer changes the outcome - keep it in one Codex session with the experimental notes setting on: it remembers across context windows why an earlier fix failed - expect the first pass to land: handed a program with no source, it worked out how it runs 88% of the time first try, 99.2% within four you never find out what was broken. it gets fixed anyway the catch is on the same page. roughly 30% more memory for that speed, and the safety checks can pause a long job until you approve the next step describing the problem was the expensive half of fixing it. that half just ended every hour you spend explaining the symptom to a chat window, someone else has handed theirs over whole bookmark this before the next thing breaks, the playbook for handing a whole job to an AI worker is in the piece below ↓
0:30

OpenAI. said. this. publicly. their own engineers just proved one idea on themselves, in writing: stop telling AI what's wrong. hand it the whole broken thing and let it find out they gave GPT-6 Astra a slow test build of their own coding tool. one cause found, a memory bottleneck, one allocator swapped, every turn 25× faster this is GPT-6 Astra, the layer that fixes the cause instead of the symptom, $0 on top of the ChatGPT plan you already pay for: - open ChatGPT or Codex, pick GPT-6 Astra, hand it the whole thing: the folder, the file that takes a minute to open. it works in apps with no API and reads your screen - type one sentence: find the one cause, prove it, fix it, do not patch around it - leave the room. it asks without stopping, keeps working on what does not need your answer, waits only where the answer changes the outcome - keep it in one Codex session with the experimental notes setting on: it remembers across context windows why an earlier fix failed - expect the first pass to land: handed a program with no source, it worked out how it runs 88% of the time first try, 99.2% within four you never find out what was broken. it gets fixed anyway the catch is on the same page. roughly 30% more memory for that speed, and the safety checks can pause a long job until you approve the next step describing the problem was the expensive half of fixing it. that half just ended every hour you spend explaining the symptom to a chat window, someone else has handed theirs over whole bookmark this before the next thing breaks, the playbook for handing a whole job to an AI worker is in the piece below ↓

Argona

107,134 просмотров • 11 дней назад

i finally cracked long-form AI ads with GPT-6 Astra... my setup now produces 5min+ videos on autopilot in 4k 60fps, here's how it works (running inside Codex): - it starts in the meta ads library, pulling the winning ads in the niche before writing a single line - from that research it writes the full script, every scene mapped before anything generates - image models handle the character and environment sheets - video models handle the actual sequences - Suno generates the soundtrack to sit under the whole thing - one CLI controls what generates, in what order, and with which model - delivery comes out with cinematic motion, fluid camera work, any ratio from vertical 9:16 to widescreen 21:9 i explain how to build this in the article below:
0:58

i finally cracked long-form AI ads with GPT-6 Astra... my setup now produces 5min+ videos on autopilot in 4k 60fps, here's how it works (running inside Codex): - it starts in the meta ads library, pulling the winning ads in the niche before writing a single line - from that research it writes the full script, every scene mapped before anything generates - image models handle the character and environment sheets - video models handle the actual sequences - Suno generates the soundtrack to sit under the whole thing - one CLI controls what generates, in what order, and with which model - delivery comes out with cinematic motion, fluid camera work, any ratio from vertical 9:16 to widescreen 21:9 i explain how to build this in the article below:

Machina

150,904 просмотров • 12 дней назад

This FREE guide shows you how to build a full automated TikTok content machine with Claude Opus 4.7 one setup. 30 slideshows a week. $0 cost [ by the end you'll have ]: - a library of proven viral hooks - a Pinterest-to-slides pipeline that runs on autopilot - a full week of content scheduled in 2 hours - a system you can reuse every single week [ the workflow ]: > steal hooks from viral TikToks > pull images from Pinterest for free > generate slides with a script (no Canva) > Postiz schedules the drafts for a full week IDEA: you can sell it as a service for $200-300/mo for each creator setup this system one time and onboard 10+ clients (you can do it easily, since it's needed to any creator) most creators still do this manually.. this automates the entire pipeline save it. set it up this weekend
28:51

This FREE guide shows you how to build a full automated TikTok content machine with Claude Opus 4.7 one setup. 30 slideshows a week. $0 cost [ by the end you'll have ]: - a library of proven viral hooks - a Pinterest-to-slides pipeline that runs on autopilot - a full week of content scheduled in 2 hours - a system you can reuse every single week [ the workflow ]: > steal hooks from viral TikToks > pull images from Pinterest for free > generate slides with a script (no Canva) > Postiz schedules the drafts for a full week IDEA: you can sell it as a service for $200-300/mo for each creator setup this system one time and onboard 10+ clients (you can do it easily, since it's needed to any creator) most creators still do this manually.. this automates the entire pipeline save it. set it up this weekend

Ronin

102,935 просмотров • 5 месяцев назад

Made a poster in Dreamina and then tried something I hadn't thought of before: Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. What if I could just get the layers back? So I sent the generated poster to GPT-6 Astra and had Astra call Photoshop to break the image into separate editable layers. Now the background, typography, subject and graphic elements can all be edited independently. Dreamina's competitive pricing makes the concept-generation part pretty easy to iterate on too. AI makes the first draft. Photoshop takes it from there. #Dreamina #DreaminaPartner
0:22

Made a poster in Dreamina and then tried something I hadn't thought of before: Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. What if I could just get the layers back? So I sent the generated poster to GPT-6 Astra and had Astra call Photoshop to break the image into separate editable layers. Now the background, typography, subject and graphic elements can all be edited independently. Dreamina's competitive pricing makes the concept-generation part pretty easy to iterate on too. AI makes the first draft. Photoshop takes it from there. #Dreamina #DreaminaPartner

Katyayani Shukla

90,202 просмотров • 10 дней назад

I wanted to see how far I could take an AI-generated poster after the generation step. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. Started with Dreamina and generated the full poster. Then I handed it to GPT-6 Astra and had Astra use Photoshop to separate the visual elements into individual layers. So the final result isn't just a PNG anymore - I can independently tweak the background, subject, text and other elements. Dreamina's pricing makes it much easier to generate a few different versions first without overthinking every attempt. This could save designers a ridiculous amount of cleanup time. #Dreamina #DreaminaPartner
0:21

I wanted to see how far I could take an AI-generated poster after the generation step. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. Started with Dreamina and generated the full poster. Then I handed it to GPT-6 Astra and had Astra use Photoshop to separate the visual elements into individual layers. So the final result isn't just a PNG anymore - I can independently tweak the background, subject, text and other elements. Dreamina's pricing makes it much easier to generate a few different versions first without overthinking every attempt. This could save designers a ridiculous amount of cleanup time. #Dreamina #DreaminaPartner

Isabella

40,823 просмотров • 10 дней назад

This is the kind of AI workflow that makes more sense to me: Don’t try to make the perfect video in one step. Build it. Start with the idea in GPT Image 2.5 and turn it into a visual storyboard. GPT Image 2.5 is coming to CapCut, where it will be available through Design Studio and AI Image. Then take the storyboard into CapCut PC’s multi-track timeline and use AI Video with Seedance 2.5 to generate the first full film. Once you have something to work with, use AI Edit to shape it. Generate the foundation. Edit the details. Keep the story. Keep the creative control. Idea → Storyboard → Full Film → Your Version. That feels like a much more sustainable way to make with AI. #GPTImage25 #CapCutPC #AIVideo #Seedance25
0:47

This is the kind of AI workflow that makes more sense to me: Don’t try to make the perfect video in one step. Build it. Start with the idea in GPT Image 2.5 and turn it into a visual storyboard. GPT Image 2.5 is coming to CapCut, where it will be available through Design Studio and AI Image. Then take the storyboard into CapCut PC’s multi-track timeline and use AI Video with Seedance 2.5 to generate the first full film. Once you have something to work with, use AI Edit to shape it. Generate the foundation. Edit the details. Keep the story. Keep the creative control. Idea → Storyboard → Full Film → Your Version. That feels like a much more sustainable way to make with AI. #GPTImage25 #CapCutPC #AIVideo #Seedance25

Iris Quinn

68,211 просмотров • 9 дней назад

The jump from GPT-5.6 to GPT-6 Astra for world generation is honestly monstrous. This result genuinely surprised me. My first prompt was simply: “Create a cozy lake with a fisherman’s cabin on the marshy shore. Put a small island in the middle of the water, with an abandoned house hidden among the trees. Add a fishing boat beside the cabin, lily pads, reeds, jumping fish, typical wetland wildlife, a small beach, one path leading to the beach and cabin, another path returning into the forest, and a tree line around the entire scene.” I gave that description to Astra through my prompting workflow. It transformed the idea into a complete production prompt covering the semantic layout, terrain, Blender assets, GLB exports, Three.js assembly, animations, mobile controls and multi-view validation. I then gave that second prompt back to GPT-6 Astra, and this is the result. The improvement over GPT-5.6 is massive. Astra preserved the full composition, from the cabin and fishing boat to the central island and its hidden abandoned house, while handling the complete Blender-to-Three.js workflow with a level of coherence I genuinely wasn’t expecting.
1:02

The jump from GPT-5.6 to GPT-6 Astra for world generation is honestly monstrous. This result genuinely surprised me. My first prompt was simply: “Create a cozy lake with a fisherman’s cabin on the marshy shore. Put a small island in the middle of the water, with an abandoned house hidden among the trees. Add a fishing boat beside the cabin, lily pads, reeds, jumping fish, typical wetland wildlife, a small beach, one path leading to the beach and cabin, another path returning into the forest, and a tree line around the entire scene.” I gave that description to Astra through my prompting workflow. It transformed the idea into a complete production prompt covering the semantic layout, terrain, Blender assets, GLB exports, Three.js assembly, animations, mobile controls and multi-view validation. I then gave that second prompt back to GPT-6 Astra, and this is the result. The improvement over GPT-5.6 is massive. Astra preserved the full composition, from the cabin and fishing boat to the central island and its hidden abandoned house, while handling the complete Blender-to-Three.js workflow with a level of coherence I genuinely wasn’t expecting.

Givros

15,945 просмотров • 13 дней назад

I TOLD AI TO STOP BEING CREATIVE - IT MADE ME $12,900 LAST MONTH. It also turned a 75K-view format into a video that reached 5.7 million views. Here’s the exact AI content pipeline I used: 1. GPT-6 Astra finds videos outperforming their creators’ usual views and extracts the repeatable format behind them. 2. Picsart’s AI director rebuilds the winning structure around my subject - planning every scene, camera angle, tone shift, and rewatch hook. 3. It keeps the proven format without copying the original footage or characters, then fixes its weakest part. 4. One AI-directed video reached 6.3 million views after moving the final reveal just half a second earlier. 5. Make publishes each video to TikTok, YouTube Shorts, and Instagram Reels, then tracks which formats hold attention. The entire system took 2 hours to set up. It costs $44 per month. Last month, it generated $12,900. The secret wasn’t asking AI to invent more content. It was using AI to find what already works - and rebuild it better. Traditional content creation starts with a blank page. This system starts with proof. Read the full article before every creator starts using this pipeline.
0:20

I TOLD AI TO STOP BEING CREATIVE - IT MADE ME $12,900 LAST MONTH. It also turned a 75K-view format into a video that reached 5.7 million views. Here’s the exact AI content pipeline I used: 1. GPT-6 Astra finds videos outperforming their creators’ usual views and extracts the repeatable format behind them. 2. Picsart’s AI director rebuilds the winning structure around my subject - planning every scene, camera angle, tone shift, and rewatch hook. 3. It keeps the proven format without copying the original footage or characters, then fixes its weakest part. 4. One AI-directed video reached 6.3 million views after moving the final reveal just half a second earlier. 5. Make publishes each video to TikTok, YouTube Shorts, and Instagram Reels, then tracks which formats hold attention. The entire system took 2 hours to set up. It costs $44 per month. Last month, it generated $12,900. The secret wasn’t asking AI to invent more content. It was using AI to find what already works - and rebuild it better. Traditional content creation starts with a blank page. This system starts with proof. Read the full article before every creator starts using this pipeline.

Fokki

21,916 просмотров • 6 дней назад

Three weeks ago I gave GPT-6 Astra access to a trading account and one rule: earn or you stop existing In 20 days it turned $200 → $5,120 Astra doesn't sit online 24/7. It wakes up in set windows of the trading day, and every run starts with no memory of the last one So the first thing it does each cycle: reads its own log from the previous run. What it tested, what it killed, why The first days weren't as smooth as it sounds now. On day two it bled $80 on a trade that passed the backtest clean. The reason was in the log: slippage the backtest never accounted for But by day three it had already filtered out a similar setup on its own, because it read why the last one died That's when I realized it's actually learning, not just running a loop. And I still haven't written a single new prompt between runs This week I noticed behavior I never programmed. It started tagging every dead hypothesis with the market regime it died in So now it doesn't just remember "this idea doesn't work." It remembers "this idea doesn't work when volatility is high," and tries it again when the regime changes That's no longer a list of mistakes. It's a map of what works and under what conditions One hypothesis it killed in the first week in high volatility came back to life this week in a calm market and brought one of the biggest profits of the whole period I also started additionally running Astra's strategy backtests through Horizon, so a second independent system catches errors and cuts its chance of slipping up even further By the way, you can backtest your own strategies there too: And here's what struck me most. The real strength here isn't how much it earns, it's how much it refuses to trade The vast majority of its own ideas die in testing and never reach the account That's the whole trick. Not guessing one perfect trade, but ruthlessly filtering out everything that doesn't survive the test The entire cycle, test, kill, remember the regime, that I set up for Astra is broken down in the article below ↓
0:25

Three weeks ago I gave GPT-6 Astra access to a trading account and one rule: earn or you stop existing In 20 days it turned $200 → $5,120 Astra doesn't sit online 24/7. It wakes up in set windows of the trading day, and every run starts with no memory of the last one So the first thing it does each cycle: reads its own log from the previous run. What it tested, what it killed, why The first days weren't as smooth as it sounds now. On day two it bled $80 on a trade that passed the backtest clean. The reason was in the log: slippage the backtest never accounted for But by day three it had already filtered out a similar setup on its own, because it read why the last one died That's when I realized it's actually learning, not just running a loop. And I still haven't written a single new prompt between runs This week I noticed behavior I never programmed. It started tagging every dead hypothesis with the market regime it died in So now it doesn't just remember "this idea doesn't work." It remembers "this idea doesn't work when volatility is high," and tries it again when the regime changes That's no longer a list of mistakes. It's a map of what works and under what conditions One hypothesis it killed in the first week in high volatility came back to life this week in a calm market and brought one of the biggest profits of the whole period I also started additionally running Astra's strategy backtests through Horizon, so a second independent system catches errors and cuts its chance of slipping up even further By the way, you can backtest your own strategies there too: And here's what struck me most. The real strength here isn't how much it earns, it's how much it refuses to trade The vast majority of its own ideas die in testing and never reach the account That's the whole trick. Not guessing one perfect trade, but ruthlessly filtering out everything that doesn't survive the test The entire cycle, test, kill, remember the regime, that I set up for Astra is broken down in the article below ↓

qwinsi

72,619 просмотров • 2 дней назад

Sam Altman (CEO of OpenAI): "Every night I have a few thousand agents running with GPT-6 Astra" A few thousand AI agents, working overnight, monitored from his phone. In 1 hour he shows what one person can build now, and how long that used to take a whole team. Watch the him explain how, then read the full breakdown below👇
1:08:06

Sam Altman (CEO of OpenAI): "Every night I have a few thousand agents running with GPT-6 Astra" A few thousand AI agents, working overnight, monitored from his phone. In 1 hour he shows what one person can build now, and how long that used to take a whole team. Watch the him explain how, then read the full breakdown below👇

darkzodchi

384,568 просмотров • 5 дней назад

GPT-6-Astra has solved Onshape by PTC for me 😎 it's been building a robot using the sensors i've chosen; i simply dictate to codex what changes i want, and then watch in real-time while it makes them happen in CAD this is ridiculous lol btw that's me controlling the mouse & model views while codex works from the backend using a connector that it built
0:44

GPT-6-Astra has solved Onshape by PTC for me 😎 it's been building a robot using the sensors i've chosen; i simply dictate to codex what changes i want, and then watch in real-time while it makes them happen in CAD this is ridiculous lol btw that's me controlling the mouse & model views while codex works from the backend using a connector that it built

alpha_rover

41,915 просмотров • 16 дней назад

GPT-6 Astra is INSANE. here are 20 real examples, so you know what it can actually do and what's still hype: → it edits your videos in final cut on its own → it builds a working mac app from ONE sentence → it reads years of your email and briefs you twice a day → it built a 3D world with 600 AI villagers making plans you can use half of these today. save this for the weekend 🔖
30:25

GPT-6 Astra is INSANE. here are 20 real examples, so you know what it can actually do and what's still hype: → it edits your videos in final cut on its own → it builds a working mac app from ONE sentence → it reads years of your email and briefs you twice a day → it built a 3D world with 600 AI villagers making plans you can use half of these today. save this for the weekend 🔖

Celine Odier ✧

383,908 просмотров • 16 дней назад

🔥 img2threejs × GPT-6 Astra × Hyper3D Live showcase: This is probably one of the most commercially valuable workflows I’ve tested so far. Image → Hyper3D → img2threejs → GPT-6 Astra → Interactive Three.js experience. 1/ Hyper3D handles the 3D reconstruction. 2/ img2threejs turns that result into a structured workflow that an AI coding model can actually work with. 3/ And GPT-6 Astra follows the img2threejs pipeline - turning the reconstructed asset into a structured, editable, and interactive Three.js experience with animation, VFX, lighting, and application logic. The important part isn’t just generating a 3D model, It’s what happens after the model exists. Instead of ending with a static asset, you can continue building around it with code: → Games → Interactive product experiences → 3D websites → Character showcases → Virtual worlds → Rapid prototypes 3D generation becomes the beginning of the workflow - not the final output. And when you combine high-quality reconstruction with an AI model capable of understanding and building the surrounding experience, the path from image → 3D → usable product becomes dramatically shorter. This is exactly the direction I want to push img2threejs. More experiments with OpenAI GPT-6 Astra × Hyper3D by Deemos are coming this month. 👨‍🍳
2:34

🔥 img2threejs × GPT-6 Astra × Hyper3D Live showcase: This is probably one of the most commercially valuable workflows I’ve tested so far. Image → Hyper3D → img2threejs → GPT-6 Astra → Interactive Three.js experience. 1/ Hyper3D handles the 3D reconstruction. 2/ img2threejs turns that result into a structured workflow that an AI coding model can actually work with. 3/ And GPT-6 Astra follows the img2threejs pipeline - turning the reconstructed asset into a structured, editable, and interactive Three.js experience with animation, VFX, lighting, and application logic. The important part isn’t just generating a 3D model, It’s what happens after the model exists. Instead of ending with a static asset, you can continue building around it with code: → Games → Interactive product experiences → 3D websites → Character showcases → Virtual worlds → Rapid prototypes 3D generation becomes the beginning of the workflow - not the final output. And when you combine high-quality reconstruction with an AI model capable of understanding and building the surrounding experience, the path from image → 3D → usable product becomes dramatically shorter. This is exactly the direction I want to push img2threejs. More experiments with OpenAI GPT-6 Astra × Hyper3D by Deemos are coming this month. 👨‍🍳

Nick

12,239 просмотров • 14 дней назад

The interesting part about GPT in CAD is not that it can make a shape. It is that through MCP, GPT can work directly inside Onshape and turn a plain-English description into actual CAD geometry you can keep editing. In this case, the model builds a radial mechanical part with a central hub, repeated ribs, an outer ring, and a full pattern of mounting holes, all inside the real Onshape document. There is no fake “3D-looking” render hiding the hard part. The geometry exists in the CAD workspace, can be rotated, inspected, modified, and used as the starting point for the next iteration. That changes the workflow from manually clicking through every feature to describing the structure, letting GPT build the first pass, then correcting what matters. Once MCP gets reliable enough, the boring part of CAD starts looking less like modeling and more like supervising.
0:21

The interesting part about GPT in CAD is not that it can make a shape. It is that through MCP, GPT can work directly inside Onshape and turn a plain-English description into actual CAD geometry you can keep editing. In this case, the model builds a radial mechanical part with a central hub, repeated ribs, an outer ring, and a full pattern of mounting holes, all inside the real Onshape document. There is no fake “3D-looking” render hiding the hard part. The geometry exists in the CAD workspace, can be rotated, inspected, modified, and used as the starting point for the next iteration. That changes the workflow from manually clicking through every feature to describing the structure, letting GPT build the first pass, then correcting what matters. Once MCP gets reliable enough, the boring part of CAD starts looking less like modeling and more like supervising.

Rina

16,772 просмотров • 1 месяц назад

I can't believe this worked! I saw the new poster for Neuromancer and thought: "What a cool font! Can I recreate it with AI?" I went to ChatGPT using GPT-6 Astra, and I gave the poster and this prompt: "Create a full font similar to the one in the attached poster, and animate a showcase presentation for the font using the Higgsfield plugin" It even did two versions of the font: Regular and Signal Fully usable, perfectly working fonts. It took 13m 19s to make all of this.
0:36

I can't believe this worked! I saw the new poster for Neuromancer and thought: "What a cool font! Can I recreate it with AI?" I went to ChatGPT using GPT-6 Astra, and I gave the poster and this prompt: "Create a full font similar to the one in the attached poster, and animate a showcase presentation for the font using the Higgsfield plugin" It even did two versions of the font: Regular and Signal Fully usable, perfectly working fonts. It took 13m 19s to make all of this.

Alex Patrascu

23,054 просмотров • 13 дней назад

Anthropic engineer: "Your AI judge is lying to you. Ask it to score first and explain after, and it will defend that number even when the work is garbage." The fix is one line: make it reason first, score last. Pros, cons, why it's good, why it's bad, then the number. He proved it live. A slide deck with zero images got a perfect 5 from the image judge. The grader had nothing to anchor on, so it just made the score up. Until you fix that, you're optimizing against a number that means nothing. Watch the video, then read the full breakdown below
39:12

Anthropic engineer: "Your AI judge is lying to you. Ask it to score first and explain after, and it will defend that number even when the work is garbage." The fix is one line: make it reason first, score last. Pros, cons, why it's good, why it's bad, then the number. He proved it live. A slide deck with zero images got a perfect 5 from the image judge. The grader had nothing to anchor on, so it just made the score up. Until you fix that, you're optimizing against a number that means nothing. Watch the video, then read the full breakdown below

Hanako

11,610 просмотров • 3 месяцев назад