正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Gpt-6 astra can do in-context learning on mobile manipulation! • Different environment • Different camera angle • Different layout No text prompt, it infers from video It even chooses when to use end-effector or joint space Trace recording after ⬇️

Axel

4,570 subscribers

67,278 次观看 • 15 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

26 条评论

Axel 的头像

Axel15 天前

The agent is asked to establish a plan based on the demonstration only It self-corrects and retries if needed Honestly it's pretty mesmerizing to see, and it will keep getting faster

Axel 的头像

Axel15 天前

The code is available here: We haven't completely cleaned it yet but your favorite agent will be able to understand our approach

Dhruv Diddi 的头像

Dhruv Diddi15 天前

Nicely done! 💯🦾👏

David Dobáš 的头像

David Dobáš15 天前

Look at the beautiful phone teleop interface

Axel 的头像

Axel15 天前

woah who built that

Robert Scoble 的头像

Robert Scoble15 天前

It is getting faster! Congrats.

Axel 的头像

Axel14 天前

🫡

Andrew Lyubovsky 的头像

Andrew Lyubovsky15 天前

Pretty Cool !!

Miguel Gregori 的头像

Miguel Gregori14 天前

Cuando el entorno cambia y el robot no pide un manual nuevo, ahí hay diseño.

NAMAN RAJ 的头像

NAMAN RAJ15 天前

Mind blown! 🤯 That's some advanced AI magic right there! 🧙‍♂️ What do you guys think, is this the future of human-AI collaboration?

AIwithMinal 的头像

AIwithMinal15 天前

Pure artistic brilliance.

SEAR 的头像

SEAR14 天前

this is exactly the kind of learning Sear is built around

ethereagle · building 的头像

ethereagle · building15 天前

no text, video only. are those frames dumped straight into Astra's context, or is there a separate encoder in front? that's copy-with-the-API vs needing your stack.

Axel 的头像

Axel15 天前

dumped straight in

atharva ☆ 的头像

atharva ☆15 天前

woah incredible

Axel 的头像

Axel15 天前

yeah am pretty stoked

Aaron 的头像

Aaron15 天前

so cool! 😎

Axel 的头像

Axel15 天前

couldn't believe it at first tbh

Tepulous 的头像

Tepulous15 天前

$20/min .....

Axel 的头像

Axel15 天前

not if you use kv-caching

RealMan Robotics 的头像

RealMan Robotics15 天前

The shift from simulation to real-world manipulation is the part that really matters. Curious to see how far this generalization can scale across tasks and environments.

AI Quanting 的头像

AI Quanting14 天前

The control space choice is the bit Id want to see stressed. Does it switch to joint space when the demo path is actually constrained, or does it settle per task type regardless?

Hibrinix 的头像

Hibrinix14 天前

Meanwhile your future mobile phone

Amogh Shrivastava 的头像

Amogh Shrivastava14 天前

that looks peak

Axel 的头像

Axel14 天前

That's because it is

Degenpark 的头像

Degenpark14 天前

end-effector choice is huge

相关视频

One shot website design outputs from GPT-6 Astra. All I told it to do was use my /scroll-craft skill and build me different websites. I told it to impress me. Very impressed.

One shot website design outputs from GPT-6 Astra. All I told it to do was use my /scroll-craft skill and build me different websites. I told it to impress me. Very impressed.

Nate Herk

31,582 次观看 • 21 天前

🚨 Prompt To Viral App In Minutes Build iOS native apps in minutes - text prompt to mobile app - free auth, payment, and backend - use top models including Fable 5.1 or Astra Do it all from one ChatLLM subscription

🚨 Prompt To Viral App In Minutes Build iOS native apps in minutes - text prompt to mobile app - free auth, payment, and backend - use top models including Fable 5.1 or Astra Do it all from one ChatLLM subscription

Abacus.AI

1,940,648 次观看 • 18 天前

Build Mobile Apps End To End - No Coding Experience Needed Use Opus 4.7, GPT 5.5 xHigh and Gemini 3.1 Pro to make magic No need to set up databases, user auth or backend Do it all in one prompt

Build Mobile Apps End To End - No Coding Experience Needed Use Opus 4.7, GPT 5.5 xHigh and Gemini 3.1 Pro to make magic No need to set up databases, user auth or backend Do it all in one prompt

Abacus.AI

44,825,331 次观看 • 4 个月前

GPT-6 Astra + Three.js = Smoothly INTERACTIVE and AWESOME. Might not even need Blender, the stuff you can build on the web now is wild. Prompt⬇️ It cut my workflow from a couple of hours down to just 30 minutes!

GPT-6 Astra + Three.js = Smoothly INTERACTIVE and AWESOME. Might not even need Blender, the stuff you can build on the web now is wild. Prompt⬇️ It cut my workflow from a couple of hours down to just 30 minutes!

padphone

60,661 次观看 • 20 天前

Sam Altman (CEO of Open AI): "You no longer need to write prompts, if you use GPT-6 Astra” In just 1 hour, he explains how to use GPT-6 Astra at a level that most people can't even imagine. After watching it, I realized I was only taking advantage of about 15% of what this tool can really do. Watch it and then read the guide l leave below on how to use it at it's fullest 👇🏼

Sam Altman (CEO of Open AI): "You no longer need to write prompts, if you use GPT-6 Astra” In just 1 hour, he explains how to use GPT-6 Astra at a level that most people can't even imagine. After watching it, I realized I was only taking advantage of about 15% of what this tool can really do. Watch it and then read the guide l leave below on how to use it at it's fullest 👇🏼

darkzodchi

805,153 次观看 • 19 天前

JUNGKOOK LIVE 🐰: When do I use AI? I use it when I have to search about something or for translations. 🐰: AI should be used in a controlled way. These days there's no difference between real and AI. How's that even different from deepfake.

JUNGKOOK LIVE 🐰: When do I use AI? I use it when I have to search about something or for translations. 🐰: AI should be used in a controlled way. These days there's no difference between real and AI. How's that even different from deepfake.

JUNGKOOK BASE

278,928 次观看 • 5 个月前

Can GPT-6 Astra actually create a 3D model like this? 🤔 I’ve been seeing people hype GPT-6 Astra looooot when it comes to 3D modeling, but can it really create 3D models with this level of detail? Wish i had access to try it,.. anyway, I created this one using Tripo as my lil submission to Tripo’s Companion Challenge where you have to create a 3D companion of your choice. I generated a bunch of different imaginary companions using GPT Image 2.0, from cute little dragons and humans to these adorable animals. After trying out a lot of different ideas, I finally settled on this panda in a bamboo forest look. I love how quickly you can go from having a random idea in your head to actually seeing it come to life, these days. That part is honestly so much fun. Now I just need to animate this little guy and turn it into an animated panda game or maybe 3D print it out haha #tripop2

Can GPT-6 Astra actually create a 3D model like this? 🤔 I’ve been seeing people hype GPT-6 Astra looooot when it comes to 3D modeling, but can it really create 3D models with this level of detail? Wish i had access to try it,.. anyway, I created this one using Tripo as my lil submission to Tripo’s Companion Challenge where you have to create a 3D companion of your choice. I generated a bunch of different imaginary companions using GPT Image 2.0, from cute little dragons and humans to these adorable animals. After trying out a lot of different ideas, I finally settled on this panda in a bamboo forest look. I love how quickly you can go from having a random idea in your head to actually seeing it come to life, these days. That part is honestly so much fun. Now I just need to animate this little guy and turn it into an animated panda game or maybe 3D print it out haha #tripop2

The Bugged Dev

160,498 次观看 • 21 天前

The interesting thing about AI filmmaking may be that the final video can have several different “authors.” GPT-6 Astra establishes the spatial logic. Seedance 2.5 interprets that setup visually. Then I bring the footage into CapCut PC and use Edit Pilot to make the editorial decisions. No single stage has to do everything. And maybe that’s actually closer to how filmmaking has always worked: different tools and people contribute different layers, while someone still decides what the final piece should be. Does AI filmmaking need one all-in-one model—or a better production pipeline? #GPT6Astra #AIVideo #Seedance25 #CapCutPC

The interesting thing about AI filmmaking may be that the final video can have several different “authors.” GPT-6 Astra establishes the spatial logic. Seedance 2.5 interprets that setup visually. Then I bring the footage into CapCut PC and use Edit Pilot to make the editorial decisions. No single stage has to do everything. And maybe that’s actually closer to how filmmaking has always worked: different tools and people contribute different layers, while someone still decides what the final piece should be. Does AI filmmaking need one all-in-one model—or a better production pipeline? #GPT6Astra #AIVideo #Seedance25 #CapCutPC

Frank

64,837 次观看 • 17 天前

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

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 次观看 • 14 天前

I love their bickering vibe 😂 🐶: You hate it when I do this so why are you doing it? 🐈: it’s different 🧸: Yeah it’s different.. The youngest usually likes this kind of thing 🐈: It’s different from what you do 🐶: What’s different from what I do to you? 🐈: I don’t usually do this to him, I’m only doing it because we’re live. You on the other hand do this whether it’s live or not 🐈: look at this!!! 🧸: If you’re jealous, you can be the youngest 🐶: Honestly…I am jealous

I love their bickering vibe 😂 🐶: You hate it when I do this so why are you doing it? 🐈: it’s different 🧸: Yeah it’s different.. The youngest usually likes this kind of thing 🐈: It’s different from what you do 🐶: What’s different from what I do to you? 🐈: I don’t usually do this to him, I’m only doing it because we’re live. You on the other hand do this whether it’s live or not 🐈: look at this!!! 🧸: If you’re jealous, you can be the youngest 🐶: Honestly…I am jealous

𝗞𝗲𝗹𝗹𝘆 ⛇ is HOME

46,236 次观看 • 7 个月前

ON THE APP: → Tap on 'Imagine' in the app → Choose 'Video' from the prompt box → Tap on 'Animate Photos' → Select up to 7 images → Write your prompt → Tap the reference image while the cursor is where you want it to appear in the prompt. Repeat for every image. → Check the settings before sending the prompt for aspect ratio, video duration, and resolution. → Hit send and wait. Now you can use the same character, object, scene, or anything else across different videos.

ON THE APP: → Tap on 'Imagine' in the app → Choose 'Video' from the prompt box → Tap on 'Animate Photos' → Select up to 7 images → Write your prompt → Tap the reference image while the cursor is where you want it to appear in the prompt. Repeat for every image. → Check the settings before sending the prompt for aspect ratio, video duration, and resolution. → Hit send and wait. Now you can use the same character, object, scene, or anything else across different videos.

Dogan Ural

27,468 次观看 • 6 个月前

This is so cool. In the next Codex update, multi agents will get a massive flexibility upgrade. "Hey Codex, when you implement this plan, I want you to delegate all the lower complexity tasks to GPT 5.3 Spark subagents" Instead of needing to create 100 different custom agent roles for different situations, you can just prompt your agent to spawn whatever model or reasoning level you want. With only natural language. No config files. No pre-defined roles. Just tell the orchestrator what to use and it listens.

This is so cool. In the next Codex update, multi agents will get a massive flexibility upgrade. "Hey Codex, when you implement this plan, I want you to delegate all the lower complexity tasks to GPT 5.3 Spark subagents" Instead of needing to create 100 different custom agent roles for different situations, you can just prompt your agent to spawn whatever model or reasoning level you want. With only natural language. No config files. No pre-defined roles. Just tell the orchestrator what to use and it listens.

am.will

128,125 次观看 • 6 个月前

A blank shape went in… and a whole dessert collection came out 🍪 This was a fun workflow to watch. Starting from a basic Blender setup, MeshyAI helped create different pastry white models, and GPT 6 Astra turned them into a complete 3D collection. The coolest part is how easy it becomes to test ideas: Want a different flavor? A different style? A completely new asset? Instead of restarting everything, I can just explore more possibilities much faster. 😝 Thanks to MeshyAI for the collaboration! Excited to keep exploring AI + 3D. 🙌 #Astra #MeshyAI #ImageTo3D #GenerativeAI

A blank shape went in… and a whole dessert collection came out 🍪 This was a fun workflow to watch. Starting from a basic Blender setup, MeshyAI helped create different pastry white models, and GPT 6 Astra turned them into a complete 3D collection. The coolest part is how easy it becomes to test ideas: Want a different flavor? A different style? A completely new asset? Instead of restarting everything, I can just explore more possibilities much faster. 😝 Thanks to MeshyAI for the collaboration! Excited to keep exploring AI + 3D. 🙌 #Astra #MeshyAI #ImageTo3D #GenerativeAI

Kylie

77,160 次观看 • 14 天前

No one warned me that in Europe, a honest mistake can land you in jail. Mistakenly entering a train that is different from the train which you bought ticket for, even when it was an honest mistake and you show it to authorities can get you a serious fine or a short jail time.

No one warned me that in Europe, a honest mistake can land you in jail. Mistakenly entering a train that is different from the train which you bought ticket for, even when it was an honest mistake and you show it to authorities can get you a serious fine or a short jail time.

Dr Penking™

791,278 次观看 • 9 个月前

FULL CLIP: Asmongold says this could change the gaming industry after reacting to the release of GPT-6 Astra, which can create worlds and games in Unreal Engine 😳👀 “This could totally change the game. Do you guys wanna do this tomorrow? I’m thinking that might be a good idea. I could try to AI-generate different video games and see how close it gets. I could make my own game”

FULL CLIP: Asmongold says this could change the gaming industry after reacting to the release of GPT-6 Astra, which can create worlds and games in Unreal Engine 😳👀 “This could totally change the game. Do you guys wanna do this tomorrow? I’m thinking that might be a good idea. I could try to AI-generate different video games and see how close it gets. I could make my own game”

Prism

67,848 次观看 • 21 天前

This GPT Image 2 prompt creates cinematic storyboard grids from your reference images while generating an original continuous sequence. You can see two different examples in the attached video. If you want a director-inspired cinematic tone, first use the separate “director language” prompt with a director name. It gives you abstract cinematic qualities without directly replicating copyrighted styles. If you don’t want that, you can simply remove that paragraph from the grid prompt. Then you can use the Seedance 2.0 prompt I shared to animate the storyboard grid into a cinematic sequence. You can find the prompts below.

This GPT Image 2 prompt creates cinematic storyboard grids from your reference images while generating an original continuous sequence. You can see two different examples in the attached video. If you want a director-inspired cinematic tone, first use the separate “director language” prompt with a director name. It gives you abstract cinematic qualities without directly replicating copyrighted styles. If you don’t want that, you can simply remove that paragraph from the grid prompt. Then you can use the Seedance 2.0 prompt I shared to animate the storyboard grid into a cinematic sequence. You can find the prompts below.

Kōda

11,369 次观看 • 4 个月前

ROSALÍA talks about what it was like to learn 13 languages to sing the songs on her new album “LUX”. “I speak a little Catalan because it’s my mother tongue. I speak a little Spanish and barely any English, but, you know… I love learning. I love learning things. So I wanted to learn different languages for a long time. I’ve been practicing on Duolingo, you know. But sometimes I’m like, ‘I need to do more.’ So while I was trying to figure out what the concept would be, because I was curious about learning from other cultures and how spirituality can be understood in many different places around the world in different ways, I was learning about different saints from all over the world. And I was reading, reading, reading so many hagiographies, hagiographies. Then I thought, ‘OK, let me put a map on the wall.’ Let me pin different stories, different women from around the world. And if I was making a song inspired by Joan of Arc, then I would do it in French. So depending on the story I wanted to reference, I would use one language or another. And then I would write about 20 different verse options and send them to a translator, a proper translator, get them back, tweak things, record, and then send them to people who would correct the pronunciation, all of it.”

ROSALÍA talks about what it was like to learn 13 languages to sing the songs on her new album “LUX”. “I speak a little Catalan because it’s my mother tongue. I speak a little Spanish and barely any English, but, you know… I love learning. I love learning things. So I wanted to learn different languages for a long time. I’ve been practicing on Duolingo, you know. But sometimes I’m like, ‘I need to do more.’ So while I was trying to figure out what the concept would be, because I was curious about learning from other cultures and how spirituality can be understood in many different places around the world in different ways, I was learning about different saints from all over the world. And I was reading, reading, reading so many hagiographies, hagiographies. Then I thought, ‘OK, let me put a map on the wall.’ Let me pin different stories, different women from around the world. And if I was making a song inspired by Joan of Arc, then I would do it in French. So depending on the story I wanted to reference, I would use one language or another. And then I would write about 20 different verse options and send them to a translator, a proper translator, get them back, tweak things, record, and then send them to people who would correct the pronunciation, all of it.”

ROSALÍA UPDATE

1,821,484 次观看 • 10 个月前

okay another demo fo Gemma4 + Falcon Perception for automated video segmentation & tracking, no human prompts needed the idea: you feed Gemma4 a few sampled frames and ask it to describe what it sees. those descriptions get passed to Falcon Perception which segments and tracks them across the full video (using ByteTrack you can steer what Gemma4 focuses on with different prompt levels: describe by visible text or brand -> dog with number 2 bib describe by spatial position -> horse on the right, horse in center, horse on the left describe by relationships -> rhinoceros walking with zebra same pipeline, different instructions ->different segmentation results. zero human labeling from raw video to tracked output. all local on M3 using mlx-vlm Prince Canuma Maziyar PANAHI Work done by Sanath Narayan Check our Falcon Perception repo:

Yasser Dahou

52,338 次观看 • 5 个月前