Загрузка видео...

Не удалось загрузить видео

На главную

Wow, Gemini 3.1 Pro just crushed one of my test problems no other model could solve. "Write a photorealistic 3D ocean simulation" 3D graphics is extremely hard. It has to encode 9-10 techniques based in physics. Being off by just 1 number can lead to bonkers results

deedydas's profile picture

Deedy

253,170 subscribers

5,046,556 просмотров • 6 месяцев назад •via X (Twitter)

ИскусствоОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

The Google Gemini can transform your questions and complex topics into custom and interactive visualizations — directly within your chat. Whether you’re rotating a molecule or simulating a complex physics system, you create 3D simulations with just one prompt in Gemini. Try starting your prompt with “show me...,” to get your interactive visualization. For the best results, try using Gemini’s Flash model.
0:18

The Google Gemini can transform your questions and complex topics into custom and interactive visualizations — directly within your chat. Whether you’re rotating a molecule or simulating a complex physics system, you create 3D simulations with just one prompt in Gemini. Try starting your prompt with “show me...,” to get your interactive visualization. For the best results, try using Gemini’s Flash model.

Google

295,315 просмотров • 3 дней назад

Gemini 3.1 Pro vs Opus 4.6 opus is consistent and relaible Prompt : Build a premium interactive isometric 3D cozy room using Three.js in one html code block, with all objects modeled in code (no external assets) and subtle ambient animations and you can do 2 things of your choice to make it better
0:12

Gemini 3.1 Pro vs Opus 4.6 opus is consistent and relaible Prompt : Build a premium interactive isometric 3D cozy room using Three.js in one html code block, with all objects modeled in code (no external assets) and subtle ambient animations and you can do 2 things of your choice to make it better

Chetaslua

37,519 просмотров • 6 месяцев назад

KIMI K3 JUST RECREATED A FUNCTIONAL GAME BOY ADVANCE IN 3D → interactive 3D model, every button and screen modeled → a game loaded and playable right inside it → camera you can rotate and zoom around the device → one single prompt, zero external assets $3 in API with K3. the same result would run about $9 with Fable 5 and $6 with Opus 4.8 this isn't generating a static image of hardware anymore, it's generating a working simulation of it, from the shell to the screen to the game running inside
0:15

KIMI K3 JUST RECREATED A FUNCTIONAL GAME BOY ADVANCE IN 3D → interactive 3D model, every button and screen modeled → a game loaded and playable right inside it → camera you can rotate and zoom around the device → one single prompt, zero external assets $3 in API with K3. the same result would run about $9 with Fable 5 and $6 with Opus 4.8 this isn't generating a static image of hardware anymore, it's generating a working simulation of it, from the shell to the screen to the game running inside

alex

38,248 просмотров • 1 месяц назад

🚨Gemini 3.6 Flash is trash I tested it on a 3D Golden Gate Bridge, and the results were awful. • I had to re-prompt it three times because it repeatedly ignored the instructions. • First attempt, instead of creating the requested .html file, it first tried to build the experience inside the Gemini app using simulations. • Then second attempt it started placing images from the web into the chat rather than actually producing the file. • Even after getting it to complete the task, the final output was dramatically worse than Gemini 3.1 Pro, which is 5 months old and now not even a top 10 model on leaderboards. This feels like a regression from Gemini 3.5 Flash and honestly, it is one of the weakest models I have tested in the past few months. Has anyone else tested Gemini 3.6 Flash yet, and are you seeing the same thing?
0:15

🚨Gemini 3.6 Flash is trash I tested it on a 3D Golden Gate Bridge, and the results were awful. • I had to re-prompt it three times because it repeatedly ignored the instructions. • First attempt, instead of creating the requested .html file, it first tried to build the experience inside the Gemini app using simulations. • Then second attempt it started placing images from the web into the chat rather than actually producing the file. • Even after getting it to complete the task, the final output was dramatically worse than Gemini 3.1 Pro, which is 5 months old and now not even a top 10 model on leaderboards. This feels like a regression from Gemini 3.5 Flash and honestly, it is one of the weakest models I have tested in the past few months. Has anyone else tested Gemini 3.6 Flash yet, and are you seeing the same thing?

Lumina

72,213 просмотров • 1 месяц назад

We released physics-intern: a simple harness for science problems! It gets models like Gemini 3.1 Pro to go from 17.7 -> 31.4, thus beating GPT 5.5 Pro. The physics-intern harness can wrap any model and via dedicated subagent boost the performance of the vanilla reasoning models. While I think more and more of these harness capability gains will be absorbed into the models (like prompting tricks disappeared over time) there is a lot to be gained right now by building good scaffolds for those models and integrating tools well. Interestingly, the exception we found that GPT 5.5 Pro actually didn't benefit from the physics-intern harness! Read more about it here: PS: I think the Harness[Model] notation is kind of nice.
0:12

We released physics-intern: a simple harness for science problems! It gets models like Gemini 3.1 Pro to go from 17.7 -> 31.4, thus beating GPT 5.5 Pro. The physics-intern harness can wrap any model and via dedicated subagent boost the performance of the vanilla reasoning models. While I think more and more of these harness capability gains will be absorbed into the models (like prompting tricks disappeared over time) there is a lot to be gained right now by building good scaffolds for those models and integrating tools well. Interestingly, the exception we found that GPT 5.5 Pro actually didn't benefit from the physics-intern harness! Read more about it here: PS: I think the Harness[Model] notation is kind of nice.

Leandro von Werra

97,424 просмотров • 3 месяцев назад

2026 marks my 10 years of being in XR. It’s amazing how much has changed or improved in this medium I used to need both a powerful PC and third-party tools to record a simple clip like this one. Wearing a headset with 1/3 of the resolution And my phone can record 3D video ❤️
0:14

2026 marks my 10 years of being in XR. It’s amazing how much has changed or improved in this medium I used to need both a powerful PC and third-party tools to record a simple clip like this one. Wearing a headset with 1/3 of the resolution And my phone can record 3D video ❤️

Brad Lynch

18,568 просмотров • 8 месяцев назад

If you think OpenAI Sora is a creative toy like DALLE, ... think again. Sora is a data-driven physics engine. It is a simulation of many worlds, real or fantastical. The simulator learns intricate rendering, "intuitive" physics, long-horizon reasoning, and semantic grounding, all by some denoising and gradient maths. I won't be surprised if Sora is trained on lots of synthetic data using Unreal Engine 5. It has to be! Let's breakdown the following video. Prompt: "Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee." - The simulator instantiates two exquisite 3D assets: pirate ships with different decorations. Sora has to solve text-to-3D implicitly in its latent space. - The 3D objects are consistently animated as they sail and avoid each other's paths. - Fluid dynamics of the coffee, even the foams that form around the ships. Fluid simulation is an entire sub-field of computer graphics, which traditionally requires very complex algorithms and equations. - Photorealism, almost like rendering with raytracing. - The simulator takes into account the small size of the cup compared to oceans, and applies tilt-shift photography to give a "minuscule" vibe. - The semantics of the scene does not exist in the real world, but the engine still implements the correct physical rules that we expect. Next up: add more modalities and conditioning, then we have a full data-driven UE that will replace all the hand-engineered graphics pipelines.
0:15

If you think OpenAI Sora is a creative toy like DALLE, ... think again. Sora is a data-driven physics engine. It is a simulation of many worlds, real or fantastical. The simulator learns intricate rendering, "intuitive" physics, long-horizon reasoning, and semantic grounding, all by some denoising and gradient maths. I won't be surprised if Sora is trained on lots of synthetic data using Unreal Engine 5. It has to be! Let's breakdown the following video. Prompt: "Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee." - The simulator instantiates two exquisite 3D assets: pirate ships with different decorations. Sora has to solve text-to-3D implicitly in its latent space. - The 3D objects are consistently animated as they sail and avoid each other's paths. - Fluid dynamics of the coffee, even the foams that form around the ships. Fluid simulation is an entire sub-field of computer graphics, which traditionally requires very complex algorithms and equations. - Photorealism, almost like rendering with raytracing. - The simulator takes into account the small size of the cup compared to oceans, and applies tilt-shift photography to give a "minuscule" vibe. - The semantics of the scene does not exist in the real world, but the engine still implements the correct physical rules that we expect. Next up: add more modalities and conditioning, then we have a full data-driven UE that will replace all the hand-engineered graphics pipelines.

Jim Fan

6,183,148 просмотров • 2 лет назад

Another big drop from Hunyuan3D by Tencent. Hunyuan3D-Buffalo 1.0 is not just another text-to-3D model. The more interesting part is its approach to 3D understanding and editing. It can understand separate parts of a complete asset, extract them, remove or replace them with prompts, and edit only the selected region while keeping the rest of the geometry unchanged. That feels like a much more useful direction for 3D AI in general: not just generating a mesh once, but actually understanding its structure and letting you continue working with it. The model combines Qwen-VL, TRELLIS and Hunyuan3D, and was trained on an impressive dataset of 87 million 3D samples. Source:
0:18

Another big drop from Hunyuan3D by Tencent. Hunyuan3D-Buffalo 1.0 is not just another text-to-3D model. The more interesting part is its approach to 3D understanding and editing. It can understand separate parts of a complete asset, extract them, remove or replace them with prompts, and edit only the selected region while keeping the rest of the geometry unchanged. That feels like a much more useful direction for 3D AI in general: not just generating a mesh once, but actually understanding its structure and letting you continue working with it. The model combines Qwen-VL, TRELLIS and Hunyuan3D, and was trained on an impressive dataset of 87 million 3D samples. Source:

Stefan 3D AI

36,034 просмотров • 24 дней назад

Apple just trained a 3D Gaussian head reconstruction model on 10,000+ subjects. Feed-forward. No test-time optimization. New identity in, reconstructed Gaussian head out. The UV-parameterized Gaussian representation decouples the number of Gaussians from the number and resolution of input images, making it practical to train with many high resolution views. And the heads are not just static either: text-conditioned identity generation, plus blendshape-driven latent animation across identities. We've been building in the 3D Gaussian Splatting space for a while. The gap between "research demo" and "works on real people at scale" is closing fast.
0:12

Apple just trained a 3D Gaussian head reconstruction model on 10,000+ subjects. Feed-forward. No test-time optimization. New identity in, reconstructed Gaussian head out. The UV-parameterized Gaussian representation decouples the number of Gaussians from the number and resolution of input images, making it practical to train with many high resolution views. And the heads are not just static either: text-conditioned identity generation, plus blendshape-driven latent animation across identities. We've been building in the 3D Gaussian Splatting space for a while. The gap between "research demo" and "works on real people at scale" is closing fast.

KIRI Engine - 3D Scanner App

12,181 просмотров • 3 месяцев назад

This is one of the worst decisions I’ve ever seen a coach make. UCF has it 1st and 10 from own 1 but Arizona State has NO TIMEOUTS! Just sneak the ball and go to the half with the lead. Fireable.
0:11

This is one of the worst decisions I’ve ever seen a coach make. UCF has it 1st and 10 from own 1 but Arizona State has NO TIMEOUTS! Just sneak the ball and go to the half with the lead. Fireable.

Chris Hassel

627,064 просмотров • 1 год назад

okay! my whole pipeline for getting fable and sol to be able to 3d model good topology hard surface game models without using any additional paid services is WORKING... we just need to dial in their lowpoly geometry and baking techniques some more, the pipeline is images > trellis > model creates the lowpoly themselves with direct headless blender interaction > bake ... this will work with both of them because you can replace sol's gptimage2 imagegen in fable's version with z-image-turbo or another quality local image model
0:15

okay! my whole pipeline for getting fable and sol to be able to 3d model good topology hard surface game models without using any additional paid services is WORKING... we just need to dial in their lowpoly geometry and baking techniques some more, the pipeline is images > trellis > model creates the lowpoly themselves with direct headless blender interaction > bake ... this will work with both of them because you can replace sol's gptimage2 imagegen in fable's version with z-image-turbo or another quality local image model

Utah teapot 🫖

11,871 просмотров • 1 месяц назад

AI 3D animations are pulling millions of views right now, not just as paid ads, but organically too this format can sell literally anything: ebooks, courses, supplements, peptides, apps, communities - whatever and you can make them in under 10 minutes, all you need is: - a script (claude with copywriting skill) - a strong first frame (Nano Banana Pro) - Veo 3 to animate it this workflow is so easy and repeatable you can automate the whole thing without any fancy tools that’s it. you just saved hours and $1000+ on a 3D artist
0:14

AI 3D animations are pulling millions of views right now, not just as paid ads, but organically too this format can sell literally anything: ebooks, courses, supplements, peptides, apps, communities - whatever and you can make them in under 10 minutes, all you need is: - a script (claude with copywriting skill) - a strong first frame (Nano Banana Pro) - Veo 3 to animate it this workflow is so easy and repeatable you can automate the whole thing without any fancy tools that’s it. you just saved hours and $1000+ on a 3D artist

MAX

267,338 просмотров • 6 месяцев назад

the best phase of a hockey goalie’s development is when they haven’t been over programmed and just do whatever they can to stop a puck even if it results in them being 10 feet out of position. Watching Brick Hockey is giving me my fix for that chaos in net
0:10

the best phase of a hockey goalie’s development is when they haven’t been over programmed and just do whatever they can to stop a puck even if it results in them being 10 feet out of position. Watching Brick Hockey is giving me my fix for that chaos in net

Fowl Hockey Dad Szn

378,609 просмотров • 2 лет назад

Not a movie trick A small number of people can actually change the size of their pupils on command Studies have confirmed this rare ability, including a 2021 case involving a German student who could voluntarily dilate and constrict his pupils by up to 2.4 mm just by engaging eye muscles no light changes, no mental imagery tricks It’s extremely uncommon but it is real.
0:15

Not a movie trick A small number of people can actually change the size of their pupils on command Studies have confirmed this rare ability, including a 2021 case involving a German student who could voluntarily dilate and constrict his pupils by up to 2.4 mm just by engaging eye muscles no light changes, no mental imagery tricks It’s extremely uncommon but it is real.

MEGA SPIRITS 🦅

24,867 просмотров • 7 месяцев назад

One of my fav X plots. Sonic would just take the problem & solve it without telling anyone, which often led to him being labeled a villain. But for him, it literally makes no sense to explain things that seem so obvious. His sensitivity to changes in nature is also a good detail
1:13

One of my fav X plots. Sonic would just take the problem & solve it without telling anyone, which often led to him being labeled a villain. But for him, it literally makes no sense to explain things that seem so obvious. His sensitivity to changes in nature is also a good detail

Vito🌿

11,661 просмотров • 9 месяцев назад

Timelapse video of a FTN 300BO Form 1 suppressor being 3d printed in PA6-CF-20 filament. So, serious question... Why haven't you filed your form 1 and 3d printed your own hearing protection? Cost of materials is less than $15 (not including the 3d printer) Private citizens can legally purchase & possess silencers in 42 (yes.. fourty two) states without a permit, and in other states with legal permission. So for under $10, a little paperwork (done and approved BEFORE you begin to make it), and a few minutes assembling & engraving you are done If not now, when?
0:19

Timelapse video of a FTN 300BO Form 1 suppressor being 3d printed in PA6-CF-20 filament. So, serious question... Why haven't you filed your form 1 and 3d printed your own hearing protection? Cost of materials is less than $15 (not including the 3d printer) Private citizens can legally purchase & possess silencers in 42 (yes.. fourty two) states without a permit, and in other states with legal permission. So for under $10, a little paperwork (done and approved BEFORE you begin to make it), and a few minutes assembling & engraving you are done If not now, when?

Wny Poker

106,362 просмотров • 7 месяцев назад

Seedance 2.0 - Cinematic Summoning VFX Prompt This prompt generates a multi-cut VFX showcase with a clear progression. It’s designed for realistic 3D with grounded physics, natural character motion and readable, production-style VFX. You don’t need to define the summon, but you can specify what is being summoned if you want control. If you leave it open, the model decides based on the character sheet. You can find gpt image 2 character sheet prompt in the quoted post. Also, this isn’t limited to summoning. You can reuse the same VFX structure for anything, just swap the effect logic. Just change the parts about summoning. Prompt in the replies 👇
0:15

Seedance 2.0 - Cinematic Summoning VFX Prompt This prompt generates a multi-cut VFX showcase with a clear progression. It’s designed for realistic 3D with grounded physics, natural character motion and readable, production-style VFX. You don’t need to define the summon, but you can specify what is being summoned if you want control. If you leave it open, the model decides based on the character sheet. You can find gpt image 2 character sheet prompt in the quoted post. Also, this isn’t limited to summoning. You can reuse the same VFX structure for anything, just swap the effect logic. Just change the parts about summoning. Prompt in the replies 👇

Kōda

28,400 просмотров • 4 месяцев назад

TURKEY JUST MADE THE MOST BULLISH BITCOIN ARGUMENT IN HISTORY. And they didn't even mean to. The Turkish Lira lost 99.99% of its value. Not 10%. Not 50%. Not 90%. 99.99%. $13,980,000,000 in T-bills sold to defend it. It's not working. This is what happens when governments print money to solve problems caused by printing money. Turkey is not an exception. Turkey is a warning. Every fiat currency in history has trended toward zero. There are only 21,000,000 Bitcoin. No government can print more. No central bank can devalue it. No T-bill sale can defend against it. The Lira chart is the most bullish Bitcoin chart ever made. And Turkey made it for us.
0:16

TURKEY JUST MADE THE MOST BULLISH BITCOIN ARGUMENT IN HISTORY. And they didn't even mean to. The Turkish Lira lost 99.99% of its value. Not 10%. Not 50%. Not 90%. 99.99%. $13,980,000,000 in T-bills sold to defend it. It's not working. This is what happens when governments print money to solve problems caused by printing money. Turkey is not an exception. Turkey is a warning. Every fiat currency in history has trended toward zero. There are only 21,000,000 Bitcoin. No government can print more. No central bank can devalue it. No T-bill sale can defend against it. The Lira chart is the most bullish Bitcoin chart ever made. And Turkey made it for us.

Crypto Tice

59,942 просмотров • 3 месяцев назад

he’s not just a rapper i want everyone to know that vocal mingyu has one of the most beautiful voices you could ever hear, a voice that makes you happy just by listening he sang it in 2025, at 28 years old… and all i can do is cry #민규
0:15

he’s not just a rapper i want everyone to know that vocal mingyu has one of the most beautiful voices you could ever hear, a voice that makes you happy just by listening he sang it in 2025, at 28 years old… and all i can do is cry #민규

ᴡᴇɴᴅʏ | 𝘴𝘩𝘢𝘬𝘦 𝘪𝘵 𝘰𝘧𝘧 🎧

26,242 просмотров • 8 месяцев назад