Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

GPT-6 Astra could take the next step in medicine "A full interactive skeleton with all 206 bones got built in two hours" ∙ Astra was pointed at an open anatomy dataset ∙ Codex wrote the entire interface, bone by bone, all 206 of them ∙ It shipped as a... show more

Zentrix⌚️

3,838 subscribers

20,901 views • 4 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

28 Comments

Zyvex4 days ago

This is the part people are underestimating. The crazy thing isn’t the 206 bones. It’s that the bottleneck is no longer knowing how to build the thing. You describe it → the model builds it → you interact with it. That changes what “learning” can look like in medicine.

Zentrix⌚️4 days ago

The shift from building models to interacting with them is huge

Peik Gabriel4 days ago

okay, I need to try this

Zentrix⌚️4 days ago

I hope everything works out for you

Alpha Mom4 days ago

two hours is the crazy part. once tools can turn a raw dataset into something this usable that fast, the bottleneck starts shifting from building to knowing what to ask for

Zentrix⌚️4 days ago

The bottleneck is quickly becoming knowing what to ask, not building it

Voyz4 days ago

the bone by bone interface is such a nice touch.

Zentrix⌚️4 days ago

Being able to isolate and explore each bone feels much more useful than just looking at a static 3D model

DEV4 days ago

Using an open anatomy dataset for this build was a smart move, data quality matters.

Zentrix⌚️4 days ago

Yes, very well said my friend

maximum4 days ago

the way AI is evolving is already starting to worry me - skynet is coming, guys 😅

Zentrix⌚️4 days ago

It’s evolving very rapidly. You can’t keep up with everything LOL

Joseph Ekene | AI & Robotics4 days ago

The exciting part is how quickly AI can turn complex anatomical data into something interactive and easy to explore. Tools like this could make medical education far more accessible. @ZentrixHQ Thanks for sharing.

Zentrix⌚️4 days ago

I'm sure this can help medicine

Trixi4 days ago

This is the most interesting thing I saw on my feed today

Zentrix⌚️4 days ago

But this is something unreal. I would really like to see it shown in lectures at medical schools

安叫兽|Bird🕊️ 🔶 BNB4 days ago

逐骨写完还做成交互界面，这速度有点离谱了

Zentrix⌚️4 days ago

I think this could be useful for learning

Brian Pridgen, MD4 days ago

Reposting is fine. But please give credit to @emmanuel_2m. Same with your other posts. Please give creators credit.

Brian Shields4 days ago

Somewhere in Rome a capuchin monk is burning tokens redesigning their crypt

Roan4 days ago

this is next level trixi

AI Mastery Guide4 days ago

206 bones in two hours, huge for med students

Elledyne Labs4 days ago

the "shipped as a claude code artifact" line is the part that matters. 206 bones is a UI problem; shipping a working tool from a prompt is a workflow problem. codex gets the first, not the second.

Squizer4 days ago

funny that no matter which model does the thinking, it still ends up shipping through Claude Code at the end. execution layer's getting more durable than any one model.

Peace4 days ago

Impressive

catman4 days ago

the Claude Code artifact sounds more interesting than the demo itself: can it expose the source and relationships behind each of the 206 bones? otherwise, it may be a polished anatomy viewer rather than a trustworthy learning tool.

Christina Haftman4 days ago

Just in time for Halloween!

Sr. X4 days ago

Link?

Related Videos

Someone gave GPT-6 and Fable 5.1 access to Canva. One smoked the other (it's not even close). Claude Fable 5.1 is on the left. GPT-6 Astra is on the right. The gap is not small. It comes down to one test (ARC-AGI 3). It drops a model into a game with no instructions and makes it work them out. Astra solved levels in fewer moves than you or I would, 96% of the time. Claude Opus 5 managed less than half of that. That's why everyone is shouting about AGI again. You can turn this on yourself in about two minutes: 1. Open the ChatGPT desktop app, switch to Work. 2. Go to Plugins, then Computer Use. Install it. 3. Switch on the server and skill toggles. 4. Allow Screen Recording and Accessibility. 5. Point it at one app and ask it do something. I wrote up the full Claude → Codex migration. Access it here → Repost ♻️ to help someone in your network.

Someone gave GPT-6 and Fable 5.1 access to Canva. One smoked the other (it's not even close). Claude Fable 5.1 is on the left. GPT-6 Astra is on the right. The gap is not small. It comes down to one test (ARC-AGI 3). It drops a model into a game with no instructions and makes it work them out. Astra solved levels in fewer moves than you or I would, 96% of the time. Claude Opus 5 managed less than half of that. That's why everyone is shouting about AGI again. You can turn this on yourself in about two minutes: 1. Open the ChatGPT desktop app, switch to Work. 2. Go to Plugins, then Computer Use. Install it. 3. Switch on the server and skill toggles. 4. Allow Screen Recording and Accessibility. 5. Point it at one app and ask it do something. I wrote up the full Claude → Codex migration. Access it here → Repost ♻️ to help someone in your network.

Charlie Hills

38,355 views • 8 days ago

Someone is building a game they dreamed of for 15 years using GPT-6 Astra and on day 10, five creature animations that used to take weeks at a 3D studio took an hour and a half, with the Scorpid running in Unity an hour after that. → Scorpid modeled in Tripo P2.0 with optimized mesh and well-organized parts for easier bone placement → Video references generated with SD 2.5 using the same workflow → About an hour and a half with GPT-6 Astra on xhigh for five animations including feedback rounds → Another hour to get it running in Unity

Someone is building a game they dreamed of for 15 years using GPT-6 Astra and on day 10, five creature animations that used to take weeks at a 3D studio took an hour and a half, with the Scorpid running in Unity an hour after that. → Scorpid modeled in Tripo P2.0 with optimized mesh and well-organized parts for easier bone placement → Video references generated with SD 2.5 using the same workflow → About an hour and a half with GPT-6 Astra on xhigh for five animations including feedback rounds → Another hour to get it running in Unity

0xMarioNawfal

38,719 views • 2 days ago

GPT-6 Astra has solved the problem of 3D anatomy tools and created an Anatomical Atlas with WebMCP support 3D anatomy tools have had a control problem for years, and almost nobody built a real fix. Every viewer forces the same workflow: click, drag, zoom, repeat, just to reach the angle a lecture or a case actually needs. A new WebMCP-enabled Anatomy Atlas skips that entirely. The interface still supports manual exploration - full 3D anatomy, cross-section scrolling, tissue retraction by hand. But WebMCP exposes those same actions to an AI agent, so setting up a specific view, isolating a structure, or producing a short walkthrough video becomes a single instruction instead of a sequence of clicks. It is not a UI overhaul. It is the same tool, plus a layer that lets software operate it the way a person would, only faster and exactly on command. The interesting part is not the atlas. It is how many other browser tools are one WebMCP layer away from being agent-operable too.

GPT-6 Astra has solved the problem of 3D anatomy tools and created an Anatomical Atlas with WebMCP support 3D anatomy tools have had a control problem for years, and almost nobody built a real fix. Every viewer forces the same workflow: click, drag, zoom, repeat, just to reach the angle a lecture or a case actually needs. A new WebMCP-enabled Anatomy Atlas skips that entirely. The interface still supports manual exploration - full 3D anatomy, cross-section scrolling, tissue retraction by hand. But WebMCP exposes those same actions to an AI agent, so setting up a specific view, isolating a structure, or producing a short walkthrough video becomes a single instruction instead of a sequence of clicks. It is not a UI overhaul. It is the same tool, plus a layer that lets software operate it the way a person would, only faster and exactly on command. The interesting part is not the atlas. It is how many other browser tools are one WebMCP layer away from being agent-operable too.

Zentrix⌚️

24,675 views • 18 hours ago

I had an early access to GPT-6 Astra and I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.

I had an early access to GPT-6 Astra and I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.

Tom Krcha

1,435,333 views • 11 days ago

This video was created in just 60 seconds with AI. I used GPT-6 Astra to create a 3D rendering that pulls apart the male anatomy into 2,234 modeled pieces. All with realistic graphics, movement, water physics, audio and sound effects.

This video was created in just 60 seconds with AI. I used GPT-6 Astra to create a 3D rendering that pulls apart the male anatomy into 2,234 modeled pieces. All with realistic graphics, movement, water physics, audio and sound effects.

Tervis Scoot

350,358 views • 6 days ago

The Sea of Thieves is open once again, with today's game update bringing changes to Bone Callers, tweaks to some old Commendations, the ability to use Free Camera while Emoting in Custom Seas and more. Read about it all in the release notes:

The Sea of Thieves is open once again, with today's game update bringing changes to Bone Callers, tweaks to some old Commendations, the ability to use Free Camera while Emoting in Custom Seas and more. Read about it all in the release notes:

Sea of Thieves

129,582 views • 1 month ago

This is sick! I built the entire city of Gurgaon in 3D using GPT-6 Astra I saw everyone building all sorts of cool demos with Astra, so I decided to give it a shot and needless to say, I was not dissapointed

This is sick! I built the entire city of Gurgaon in 3D using GPT-6 Astra I saw everyone building all sorts of cool demos with Astra, so I decided to give it a shot and needless to say, I was not dissapointed

Yajat Gulati

49,822 views • 8 days ago

THIS GUY BUILT A HABBO HOTEL CLONE IN 2 HOURS WITH GPT-6 ASTRA he didn't use a game engine, blender, 3d models, or asset packs > astra spun up a local site on his pc > built the entire thing in svgs and javascript > every character, every piece of furniture, the floors, the walls, all vector shapes drawn in code > isometric rooms and animated avatars > lighting, shadows and depth all faked in 2d he ran astra ultra at 2x speed and it ate about 42% of his weekly usage on the $100 pro plan so roughly $42 and one afternoon assets were always the issue in the 3d space (you either learned blender or you paid someone) now you can literally describe it and it draws itself

THIS GUY BUILT A HABBO HOTEL CLONE IN 2 HOURS WITH GPT-6 ASTRA he didn't use a game engine, blender, 3d models, or asset packs > astra spun up a local site on his pc > built the entire thing in svgs and javascript > every character, every piece of furniture, the floors, the walls, all vector shapes drawn in code > isometric rooms and animated avatars > lighting, shadows and depth all faked in 2d he ran astra ultra at 2x speed and it ate about 42% of his weekly usage on the $100 pro plan so roughly $42 and one afternoon assets were always the issue in the 3d space (you either learned blender or you paid someone) now you can literally describe it and it draws itself

Om Patel

20,949 views • 8 days ago

What you see in 1st video was after a couple of hours of Astra porting. This is what it looks like now. Blender optimized assets, car physics, police pursuits, missions, cutscenes, audio dialogue and more behaviors. Still very imperfect, but way better than v1. Keep in mind this is not building it from existing source code. People pointed out the PC source code is online, which I wasn't aware of and kind of takes the fun out of seeing Astra pick the game apart and attempt to rebuild it for web. There are still more things missing from the game. But you're looking at in total, around 7-8 hours of Astra picking apart the PS2 game files and attempting to rebuild in an environment this game was never intended to run in. Would the result have been better and taken less time if I used the leaked PC source code? For sure. But it wouldn't have been nearly as fun seeing Astra dig in and try piecing things together from scratch without the source.

What you see in 1st video was after a couple of hours of Astra porting. This is what it looks like now. Blender optimized assets, car physics, police pursuits, missions, cutscenes, audio dialogue and more behaviors. Still very imperfect, but way better than v1. Keep in mind this is not building it from existing source code. People pointed out the PC source code is online, which I wasn't aware of and kind of takes the fun out of seeing Astra pick the game apart and attempt to rebuild it for web. There are still more things missing from the game. But you're looking at in total, around 7-8 hours of Astra picking apart the PS2 game files and attempting to rebuild in an environment this game was never intended to run in. Would the result have been better and taken less time if I used the leaked PC source code? For sure. But it wouldn't have been nearly as fun seeing Astra dig in and try piecing things together from scratch without the source.

Dwayne

21,360 views • 6 days ago

GPT-6 Astra is now the best-performing frontier model for antibody developability prediction in our benchmark. 🧬 Finding an antibody that binds is only the beginning. Will it aggregate? Will it stay stable? Can it actually behave like a drug? GPT-6 Astra predicts these developability properties better than the other frontier models we tested. 🤯 And yes, the interactive visualization showing how an antibody actually works was also built with Astra in about 1 hour. This model looks seriously powerful. Congrats gbt Sam Altman #insilicoSOTAFM

GPT-6 Astra is now the best-performing frontier model for antibody developability prediction in our benchmark. 🧬 Finding an antibody that binds is only the beginning. Will it aggregate? Will it stay stable? Can it actually behave like a drug? GPT-6 Astra predicts these developability properties better than the other frontier models we tested. 🤯 And yes, the interactive visualization showing how an antibody actually works was also built with Astra in about 1 hour. This model looks seriously powerful. Congrats gbt Sam Altman #insilicoSOTAFM

Andrew Aiginin

303,491 views • 4 days ago

Astra began to saturate a computer-use eval we haven’t even released yet. Astra was not only able to kill several hostile mobs in Minecraft, but it made it all the way to building a Nether portal in less than three hours. We believe that if we ran it longer, it would beat the game. Astra was able to do things like tower up to kill a horde of zombies, trap a skeleton inside a hole to dodge its arrows, craft a boat, and navigate back to its base. Here is the full 3 hour play through. All of this was without any specialized harness: pure computer use.

Astra began to saturate a computer-use eval we haven’t even released yet. Astra was not only able to kill several hostile mobs in Minecraft, but it made it all the way to building a Nether portal in less than three hours. We believe that if we ran it longer, it would beat the game. Astra was able to do things like tower up to kill a horde of zombies, trap a skeleton inside a hole to dodge its arrows, craft a boat, and navigate back to its base. Here is the full 3 hour play through. All of this was without any specialized harness: pure computer use.

Vals AI

30,212 views • 6 days ago

$I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)$

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

195,173 views • 1 year ago

GPT 6 Astra one shotted a bug in BridgeMind that no model could solve in 6 months. Fable 5 failed. Fable 5.1 failed. Opus 5, Sol, Grok 4.6, all failed. Astra fixed it on the first prompt. Then it rebuilt my office in Blender from photos. Built a racing game in 13 minutes that took Fable 5.1 two hours. Cut OpenAI's hallucination rate nearly in half. All while using a third of the tokens. Full review is out now. I do not know how Anthropic survives this.

GPT 6 Astra one shotted a bug in BridgeMind that no model could solve in 6 months. Fable 5 failed. Fable 5.1 failed. Opus 5, Sol, Grok 4.6, all failed. Astra fixed it on the first prompt. Then it rebuilt my office in Blender from photos. Built a racing game in 13 minutes that took Fable 5.1 two hours. Cut OpenAI's hallucination rate nearly in half. All while using a third of the tokens. Full review is out now. I do not know how Anthropic survives this.

BridgeMind

37,762 views • 8 days ago

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

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

41,351 views • 9 days ago

AI IS GETTING WAY TOO ADVANCED I asked Astra 6 to build a 3D human brain, then break it apart in a cinematic walkthrough explaining what each section does Two hours later, this is what I got This kind of production used to take WEEKS and cost $5,000 Imagine what this could do a year from now

AI IS GETTING WAY TOO ADVANCED I asked Astra 6 to build a 3D human brain, then break it apart in a cinematic walkthrough explaining what each section does Two hours later, this is what I got This kind of production used to take WEEKS and cost $5,000 Imagine what this could do a year from now

Jeremy

12,585 views • 5 days ago

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 views • 3 days ago

$I was wrong. I used to tell people that I would never go to a medical doctor unless it was for a broken bone, fracture or some form of structural damage. After having an experience like that I decided I really don't wanna go to a hospital or medical doctor because all they're gonna do is put my bone back in place and then put it in a cast for the next couple months and I'm gonna wonder later on why it never feels the same after locking my bone into the same position. It doesn't make sense to me. Animals in the wild break bones all of the time and fully recover, as long as they don't get eaten by a predator. If I ever have any structural damage again in the future or broken bones I'm gonna use the animal method: just fast, lay down in the sun and let nature heal me.$

I was wrong. I used to tell people that I would never go to a medical doctor unless it was for a broken bone, fracture or some form of structural damage. After having an experience like that I decided I really don't wanna go to a hospital or medical doctor because all they're gonna do is put my bone back in place and then put it in a cast for the next couple months and I'm gonna wonder later on why it never feels the same after locking my bone into the same position. It doesn't make sense to me. Animals in the wild break bones all of the time and fully recover, as long as they don't get eaten by a predator. If I ever have any structural damage again in the future or broken bones I'm gonna use the animal method: just fast, lay down in the sun and let nature heal me.

Riley Check

23,107 views • 5 months ago

Sam Altman said on camera at Stripe Sessions that we are in an insane area, stuck with old devices and old operating systems. The OS and the browser are built for humans clicking. Both get rewritten around agents that do not click. Two years deep building agents. Sharpest framing I have heard a frontier lab CEO put on the next interface. ↓ Read it before the gap locks in The part nobody is sitting with: >the chat window is the old interface >the new one is an agent in a loop with your machine >the gap between people prompting and people running agents is forming right now >in six months it will be permanent Open Claude, type a question, copy the answer, paste it into VS Code. The average dev runs this loop every day. They think they are using AI. That is 5% of what these tools can do. The people pulling ahead do not prompt. They build harnesses. They run agents in loops. Same model. Different output. Full 2026 agent playbook in the article below here:

Sam Altman said on camera at Stripe Sessions that we are in an insane area, stuck with old devices and old operating systems. The OS and the browser are built for humans clicking. Both get rewritten around agents that do not click. Two years deep building agents. Sharpest framing I have heard a frontier lab CEO put on the next interface. ↓ Read it before the gap locks in The part nobody is sitting with: >the chat window is the old interface >the new one is an agent in a loop with your machine >the gap between people prompting and people running agents is forming right now >in six months it will be permanent Open Claude, type a question, copy the answer, paste it into VS Code. The average dev runs this loop every day. They think they are using AI. That is 5% of what these tools can do. The people pulling ahead do not prompt. They build harnesses. They run agents in loops. Same model. Different output. Full 2026 agent playbook in the article below here:

Rohit

120,600 views • 3 months ago