Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

HydroFX 1.5 is seriously fast. With up to 2× faster simulation speeds, iterating on fluid shots feels much more responsive. This underwater simulation was created in HydroFX 1.5 and rendered in Blender Cycles. #HydroFX #Blender #VFX #FluidSimulation

Jeremy White

1,660 subscribers

50,874 görüntüleme • 2 gün önce •via X (Twitter)

Sanat Bilim & Teknoloji Eğitim #HydroFX #Blender #VFX #FluidSimulation

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Free tool: standalone GPU FLIP fluid simulator Storm HydroFX is free in beta The promising new tool can export liquid #simulation in Alembic format, for use in other CG software like #3dsMax, #Blender or #UnrealEngine #VFX #motiongraphics Storm VFX

Free tool: standalone GPU FLIP fluid simulator Storm HydroFX is free in beta The promising new tool can export liquid #simulation in Alembic format, for use in other CG software like #3dsMax, #Blender or #UnrealEngine #VFX #motiongraphics Storm VFX

CG Channel

22,913 görüntüleme • 10 ay önce

Blender was very useful at benuts on the ambitious series We Come in Peace 🚀 Alongside Maya & Houdini for classic VFX, it excelled on more artistic shots. Geometry Nodes enabled fast procedural generation of mushrooms and alien eggs. Here are a few Blender shots 👇 #b3d

Blender was very useful at benuts on the ambitious series We Come in Peace 🚀 Alongside Maya & Houdini for classic VFX, it excelled on more artistic shots. Geometry Nodes enabled fast procedural generation of mushrooms and alien eggs. Here are a few Blender shots 👇 #b3d

Thomas Marcos

10,746 görüntüleme • 6 ay önce

Summer Cammy low-res preview Another EEVEE test. I fixed the simulation issues and got a good workflow for working fast with this rig. Low-res render at only 16 samples. Besides the film grain/music, everything was done in Blender+EEVEE in realtime, including compositing/grade

Summer Cammy low-res preview Another EEVEE test. I fixed the simulation issues and got a good workflow for working fast with this rig. Low-res render at only 16 samples. Besides the film grain/music, everything was done in Blender+EEVEE in realtime, including compositing/grade

A$AP BERG

165,130 görüntüleme • 5 ay önce

this is how it looks in blender so you can see the actual twist bones working! i know some just use 1 twist bone for this but i found it much more natural to use 2 with different influence 🙂‍↕️

this is how it looks in blender so you can see the actual twist bones working! i know some just use 1 twist bone for this but i found it much more natural to use 2 with different influence 🙂‍↕️

𝗞𝗔𝗥𝗜𝗛𝗔 🌘🍀 3D VRoid Artist ☻

42,159 görüntüleme • 10 ay önce

Unreal Engine's built-in VFX system, Niagara, can be used to create cinematic effects that run completely in real-time. In this example focused on Automotive visualization, Jesse Pitela(Jesse Pitela) is layering thousands of GPU particles for snow flakes, meshes for ice chunks, and a Niagara Fluids smoke simulation on top, to show the car interacting with its environment❄️

Unreal Engine's built-in VFX system, Niagara, can be used to create cinematic effects that run completely in real-time. In this example focused on Automotive visualization, Jesse Pitela(Jesse Pitela) is layering thousands of GPU particles for snow flakes, meshes for ice chunks, and a Niagara Fluids smoke simulation on top, to show the car interacting with its environment❄️

Unreal Engine

31,912 görüntüleme • 4 ay önce

A visualisation of different velocity factors in a PCB. Both simulations use the same excitation and port parameters. Only the permittivity is different, showing how the signal travels much faster in low Dk dielectrics. This simulation shows an embedded trace. A signal on an outer layer also travels faster because part of the EM field propagates through air, which has a Dk very close to 1

A visualisation of different velocity factors in a PCB. Both simulations use the same excitation and port parameters. Only the permittivity is different, showing how the signal travels much faster in low Dk dielectrics. This simulation shows an embedded trace. A signal on an outer layer also travels faster because part of the EM field propagates through air, which has a Dk very close to 1

Lukas Henkel

35,256 görüntüleme • 1 yıl önce

If you think this is just another silly demo made with AI, read this post. You might change your mind, because this demo is about MATH. What you see on the screen is not a render from Blender (obviously, it’s not that good). It’s a three.js app built with Toolcraft. Available on the web and rendered in real time(link in the comments). But Blender still has a lot to do with it. Blender has Geometry Nodes - a powerful node-based system for creating and manipulating procedural geometry. In other words, it’s math. And math is a universal language. And who do you think is pretty good at math? >>> AI. Now you can download or buy Blender files from marketplaces, and when they contain Geometry Nodes for procedural animations, objects, surfaces, or effects, you can transfer that logic to the web. Make it real-time, make it interactive. Materials are a separate story, of course. They can still suck unless you use the right tricks: PBR, HDRIs, material blending, displacement, and faked surface relief. So why is Blender important here? Blender is open source, and many tools around it are open source too. An AI trained on their code. That means it can translate the math from one environment to another quite accurately. If you’ve been struggling to reproduce some idea with AI that you had in your head or seen in some references, and it has something to do with Geometry Nodes, and you can find that idea or a close one in the Blender ecosystem - it means you can transfer it to the web. Thank me later.

If you think this is just another silly demo made with AI, read this post. You might change your mind, because this demo is about MATH. What you see on the screen is not a render from Blender (obviously, it’s not that good). It’s a three.js app built with Toolcraft. Available on the web and rendered in real time(link in the comments). But Blender still has a lot to do with it. Blender has Geometry Nodes - a powerful node-based system for creating and manipulating procedural geometry. In other words, it’s math. And math is a universal language. And who do you think is pretty good at math? >>> AI. Now you can download or buy Blender files from marketplaces, and when they contain Geometry Nodes for procedural animations, objects, surfaces, or effects, you can transfer that logic to the web. Make it real-time, make it interactive. Materials are a separate story, of course. They can still suck unless you use the right tricks: PBR, HDRIs, material blending, displacement, and faked surface relief. So why is Blender important here? Blender is open source, and many tools around it are open source too. An AI trained on their code. That means it can translate the math from one environment to another quite accurately. If you’ve been struggling to reproduce some idea with AI that you had in your head or seen in some references, and it has something to do with Geometry Nodes, and you can find that idea or a close one in the Blender ecosystem - it means you can transfer it to the web. Thank me later.

Alex Barashkov

28,300 görüntüleme • 1 ay önce

Elon Musk: My life feels surreal. It makes me believe in simulation theory. “Yeah, I mean I didn't think it would be when I was young, but my life feels somewhat surreal. I can't believe these things are actually happening. It makes me believe in simulation theory where it's like, well this like the things I'm doing are so preposterous that it's hard to believe they're real. I mean we've got Starship, which is the largest, most powerful flying object ever made, and we intend to launch that more than once per hour.” The Economist interview with Elon Musk, July 23, 2026.

Elon Musk: My life feels surreal. It makes me believe in simulation theory. “Yeah, I mean I didn't think it would be when I was young, but my life feels somewhat surreal. I can't believe these things are actually happening. It makes me believe in simulation theory where it's like, well this like the things I'm doing are so preposterous that it's hard to believe they're real. I mean we've got Starship, which is the largest, most powerful flying object ever made, and we intend to launch that more than once per hour.” The Economist interview with Elon Musk, July 23, 2026.

ELON CLIPS

32,191 görüntüleme • 26 gün önce

🚨 This is Iran’s Fattah Hypersonic Missile — used in strikes on Israel. With a range of 1,400 km and speeds up to Mach 15, it can hit targets like Tel Aviv in under 4 minutes, too fast for most missile defense systems to intercept

🚨 This is Iran’s Fattah Hypersonic Missile — used in strikes on Israel. With a range of 1,400 km and speeds up to Mach 15, it can hit targets like Tel Aviv in under 4 minutes, too fast for most missile defense systems to intercept

Defence Index

428,236 görüntüleme • 1 yıl önce

Blender MCP w/ Codex 5.5 or OPUS 4.8 is seriously pretty cracked... This entire block out was one-shot with a single prompt in about 15 minutes. Only problem I am having now is getting Seedance to use it properly 😅 Please feel free to use it and post your results below 👇

Blender MCP w/ Codex 5.5 or OPUS 4.8 is seriously pretty cracked... This entire block out was one-shot with a single prompt in about 15 minutes. Only problem I am having now is getting Seedance to use it properly 😅 Please feel free to use it and post your results below 👇

A.I.Warper

24,752 görüntüleme • 1 ay önce

🔥 Seedance 2.5 is finally here on Loova AI! I tried it with this luxury sunglasses concept, and the results are seriously impressive. ✨ From the unboxing to the close-up product shots and wearing the sunglasses, the motion feels smoother, more cinematic, and the character consistency is noticeably better. The product details also stay sharp and realistic throughout. 🔥 Really enjoying creating with Seedance 2.5 on LoovaAI!

🔥 Seedance 2.5 is finally here on Loova AI! I tried it with this luxury sunglasses concept, and the results are seriously impressive. ✨ From the unboxing to the close-up product shots and wearing the sunglasses, the motion feels smoother, more cinematic, and the character consistency is noticeably better. The product details also stay sharp and realistic throughout. 🔥 Really enjoying creating with Seedance 2.5 on LoovaAI!

Romana

188,102 görüntüleme • 10 gün önce

🚨BREAKING: The beta test of Blender Cycles on The Render Network is going great!! With $RENDER, a rendering job by Omid Pakbin took less than 10 minutes instead of 28 hours!! This is the largest #AI / #GPU integration ever seen in the crypto space. No one will ever come close to $RENDER and here's why ✍️ With Blender 🔶 Cycles integrated on the Render Network, millions of artists from the leading open source 3D ecosystem can harness near unlimited high performance decentralized GPU cloud rendering power on Render. The tasks performed by the millions of Blender users require heavy GPU demands. These tasks will result in many $RENDER tokens being burned, as the burning mechanism is tied 1:1 to the GPU usage of the The Render Network There is literally no #AI altcoin that has the partnerships or real utility that $RENDER provides. Forget "The next $RENDER". Once this integration goes fully live, the burning numbers of $RENDER will explode and you will see the biggest fomo ever seen in crypto.

🚨BREAKING: The beta test of Blender Cycles on The Render Network is going great!! With $RENDER, a rendering job by Omid Pakbin took less than 10 minutes instead of 28 hours!! This is the largest #AI / #GPU integration ever seen in the crypto space. No one will ever come close to $RENDER and here's why ✍️ With Blender 🔶 Cycles integrated on the Render Network, millions of artists from the leading open source 3D ecosystem can harness near unlimited high performance decentralized GPU cloud rendering power on Render. The tasks performed by the millions of Blender users require heavy GPU demands. These tasks will result in many $RENDER tokens being burned, as the burning mechanism is tied 1:1 to the GPU usage of the The Render Network There is literally no #AI altcoin that has the partnerships or real utility that $RENDER provides. Forget "The next $RENDER". Once this integration goes fully live, the burning numbers of $RENDER will explode and you will see the biggest fomo ever seen in crypto.

D0c Crypto ⭕️

15,672 görüntüleme • 1 yıl önce

NEW STARLINK GIGABIT DISHES INCOMING—FASTER THAN FIBER? SpaceX is turning up the heat with its next-gen Starlink gigabit connection gear! New dishes are in the works: * 2 Gigs, No Wires – New dish pushes speeds up to 2 Gbps. Blink and you’ll miss your download. * Next-Level Mini – A souped-up follow-up to the Starlink Mini is already in the pipeline. * Waiting on Launch – Needs FCC clearance and a Starship boost to get those V3 satellites in orbit. * Fiber, Who? – Tighter beams. Lower lag. Bigger bandwidth. Space-based internet just got real. Expect business users to get first dibs for now—but don’t blink! The future of lightning-fast satellite internet is closing in. Source: PCMag

NEW STARLINK GIGABIT DISHES INCOMING—FASTER THAN FIBER? SpaceX is turning up the heat with its next-gen Starlink gigabit connection gear! New dishes are in the works: * 2 Gigs, No Wires – New dish pushes speeds up to 2 Gbps. Blink and you’ll miss your download. * Next-Level Mini – A souped-up follow-up to the Starlink Mini is already in the pipeline. * Waiting on Launch – Needs FCC clearance and a Starship boost to get those V3 satellites in orbit. * Fiber, Who? – Tighter beams. Lower lag. Bigger bandwidth. Space-based internet just got real. Expect business users to get first dibs for now—but don’t blink! The future of lightning-fast satellite internet is closing in. Source: PCMag

Mario Nawfal

684,310 görüntüleme • 1 yıl önce

How to Make Homemade Mayo. It’s creamy, delicious, and avoids the usual risks of raw eggs. Ingredients (makes about 1–1.5 cups) 🥚 4–5 boiled eggs (peeled) 💧 Water (a splash, to help blending — roughly 2–4 tbsp) 🍋 Lemon juice (fresh, about 1–2 tbsp or to taste) 🫒 Olive oil (several tablespoons — added gradually, maybe ¼–⅓ cup total) 🧂 Pinch of salt (to taste) Optional add-ins (common for flavor): mustard, garlic powder, black pepper, or a touch of vinegar. Step-by-Step Instructions 1. Place the peeled boiled eggs in a wide-mouth jar or blending container. 2. Add a splash of water to loosen things up. 3. Pour in lemon juice and a pinch of salt. 4. Add olive oil (start with less and add more as needed for richness and emulsification). 5. Insert an immersion blender (stick blender) and blend everything until completely smooth and creamy. It transforms quickly into thick, classic-looking mayonnaise. 6. Taste and adjust seasoning (more salt, lemon, or oil if needed). Done! Store in the fridge for up to a week. Pro Tip: Use a narrow jar for the immersion blender so everything blends evenly without splatter. If it’s too thick, add a tiny bit more water or lemon juice.

How to Make Homemade Mayo. It’s creamy, delicious, and avoids the usual risks of raw eggs. Ingredients (makes about 1–1.5 cups) 🥚 4–5 boiled eggs (peeled) 💧 Water (a splash, to help blending — roughly 2–4 tbsp) 🍋 Lemon juice (fresh, about 1–2 tbsp or to taste) 🫒 Olive oil (several tablespoons — added gradually, maybe ¼–⅓ cup total) 🧂 Pinch of salt (to taste) Optional add-ins (common for flavor): mustard, garlic powder, black pepper, or a touch of vinegar. Step-by-Step Instructions 1. Place the peeled boiled eggs in a wide-mouth jar or blending container. 2. Add a splash of water to loosen things up. 3. Pour in lemon juice and a pinch of salt. 4. Add olive oil (start with less and add more as needed for richness and emulsification). 5. Insert an immersion blender (stick blender) and blend everything until completely smooth and creamy. It transforms quickly into thick, classic-looking mayonnaise. 6. Taste and adjust seasoning (more salt, lemon, or oil if needed). Done! Store in the fridge for up to a week. Pro Tip: Use a narrow jar for the immersion blender so everything blends evenly without splatter. If it’s too thick, add a tiny bit more water or lemon juice.

🦅 Eagle Wings 🦅

32,448 görüntüleme • 3 ay önce

This was my birthday splurge yesterday. It’s a one and done recipe and doesn’t trigger me to want to eat a whole bucketful. Butter Powder Espresso Mug Cake 6g carbs per serving 1 egg 4 tbs butter powder 1.5 tbs unsweetened cocoa 1 tsp espresso powder 1/2 tbs vanilla 2 tbs melted butter Sweetener of choice Air fry 8 minutes at 350 or bake in oven at 350 for 15-20 minutes. To make an easy cream cheese whipped cream, use an immersion blender on 1/4 cup cream, sweetener, vanilla and 2 tbs cream cheese or mascarpone.

This was my birthday splurge yesterday. It’s a one and done recipe and doesn’t trigger me to want to eat a whole bucketful. Butter Powder Espresso Mug Cake 6g carbs per serving 1 egg 4 tbs butter powder 1.5 tbs unsweetened cocoa 1 tsp espresso powder 1/2 tbs vanilla 2 tbs melted butter Sweetener of choice Air fry 8 minutes at 350 or bake in oven at 350 for 15-20 minutes. To make an easy cream cheese whipped cream, use an immersion blender on 1/4 cup cream, sweetener, vanilla and 2 tbs cream cheese or mascarpone.

Cary Kelly

37,846 görüntüleme • 4 ay önce

I just ran Gemma 4 31B on @CerebrasSystems at 1,800+ tokens/sec and it's multimodal. For context: that's 35x faster than a typical GPU endpoint, and the first token (reasoning included) lands in 1.5 seconds. This isn't a benchmark slide, I recorded the inference live. Prompt I used: "Create a simulation of an iPhone. Include at least one working dummy note taking app, a functional notification pulldown, high quality graphics, single HTML file, any libs via CDN." - Generation time: 3 seconds. - Notes app worked. - Notification panel worked. - Rendered first try. This is what wafer-scale inference unlocks, not just "faster," but a different category of product. When generation is this fast, you stop waiting and start iterating in real time. Why this matters: Gemma 4 31B is Google DeepMind's flagship open weight model, Apache 2.0 licensed, dense (not MoE), and built for efficiency over raw parameter count. It scores close to Claude Haiku 4.5 on the Artificial Analysis Intelligence Index (30 vs 29) but runs ~18x faster on Cerebras. It's also the first multimodal model on Cerebras's platform, meaning you can now feed it screenshots, documents, charts, and UI states at wafer scale speed. # Applications I'm most excited about: - Screenshot → Insight: Drop in a dashboard or document screenshot, get structured findings back instantly. no waiting, no batching. - Live UI generation: Full interactive interfaces (like my iPhone sim) generated and rendered in under 2 seconds. - Screenshot -> Patch: Feed it a broken UI + console error, get a minimal code fix and verification steps back. - Computer use & agentic loops: See -> reason -> act - verify, fast enough to keep a human in the loop instead of waiting on the model. - Long context summarization: Full research reports condensed into decision ready summaries you can read and requery in one sitting. The bigger unlock isn't the speed number itself, it's that agentic and multimodal loops (see -> reason -> output -> tool call -> verify -> retry) finally run in real time instead of feeling sluggish. As Logan Kilpatrick (Logan Kilpatrick) put it: "If every model was doing 2,000 tokens per second, you wouldn't build the same product and just have it be faster, you'd build different products." Gemma 4 31B is live now on Cerebras Inference Cloud in public preview. If you're building multimodal, agentic, or real time apps, this is worth testing today. What would you build with such insane inference throughput?

I just ran Gemma 4 31B on @CerebrasSystems at 1,800+ tokens/sec and it's multimodal. For context: that's 35x faster than a typical GPU endpoint, and the first token (reasoning included) lands in 1.5 seconds. This isn't a benchmark slide, I recorded the inference live. Prompt I used: "Create a simulation of an iPhone. Include at least one working dummy note taking app, a functional notification pulldown, high quality graphics, single HTML file, any libs via CDN." - Generation time: 3 seconds. - Notes app worked. - Notification panel worked. - Rendered first try. This is what wafer-scale inference unlocks, not just "faster," but a different category of product. When generation is this fast, you stop waiting and start iterating in real time. Why this matters: Gemma 4 31B is Google DeepMind's flagship open weight model, Apache 2.0 licensed, dense (not MoE), and built for efficiency over raw parameter count. It scores close to Claude Haiku 4.5 on the Artificial Analysis Intelligence Index (30 vs 29) but runs ~18x faster on Cerebras. It's also the first multimodal model on Cerebras's platform, meaning you can now feed it screenshots, documents, charts, and UI states at wafer scale speed. # Applications I'm most excited about: - Screenshot → Insight: Drop in a dashboard or document screenshot, get structured findings back instantly. no waiting, no batching. - Live UI generation: Full interactive interfaces (like my iPhone sim) generated and rendered in under 2 seconds. - Screenshot -> Patch: Feed it a broken UI + console error, get a minimal code fix and verification steps back. - Computer use & agentic loops: See -> reason -> act - verify, fast enough to keep a human in the loop instead of waiting on the model. - Long context summarization: Full research reports condensed into decision ready summaries you can read and requery in one sitting. The bigger unlock isn't the speed number itself, it's that agentic and multimodal loops (see -> reason -> output -> tool call -> verify -> retry) finally run in real time instead of feeling sluggish. As Logan Kilpatrick (Logan Kilpatrick) put it: "If every model was doing 2,000 tokens per second, you wouldn't build the same product and just have it be faster, you'd build different products." Gemma 4 31B is live now on Cerebras Inference Cloud in public preview. If you're building multimodal, agentic, or real time apps, this is worth testing today. What would you build with such insane inference throughput?

Alok

12,962 görüntüleme • 1 ay önce

𝗣𝗼𝗽𝘂𝗹𝗮𝗿 𝗼𝗽𝗶𝗻𝗶𝗼𝗻: "𝗝𝘂𝘀𝘁 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲 𝗺𝗼𝗿𝗲 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗶𝗼𝗻 𝗱𝗮𝘁𝗮." After working with many 𝗿𝗼𝗯𝗼𝘁 𝗺𝗮𝗻𝗶𝗽𝘂𝗹𝗮𝘁𝗶𝗼𝗻 teams who've fallen into the simulation trap, here's what I've learned: Simulation teaches your robot to be really, really good at simulation. Unlike blind locomotion policies that can get away with sim-to-real transfer because they rely mainly on proprioception and contact forces, 𝘃𝗶𝘀𝗶𝗼𝗻-𝗴𝘂𝗶𝗱𝗲𝗱 𝗺𝗮𝗻𝗶𝗽𝘂𝗹𝗮𝘁𝗶𝗼𝗻 𝗶𝘀 𝗲𝘅𝘁𝗿𝗲𝗺𝗲𝗹𝘆 𝘀𝗲𝗻𝘀𝗶𝘁𝗶𝘃𝗲 𝘁𝗼 𝘃𝗶𝘀𝘂𝗮𝗹 𝗱𝗼𝗺𝗮𝗶𝗻 𝗴𝗮𝗽. The subtle differences accumulate: - Simulated friction vs real surface textures - Perfect lighting vs shadows, reflections, glare - Ideal object geometries vs manufacturing tolerances - Instantaneous sensor readings vs real-world noise and latency - Clean backgrounds vs cluttered, dynamic environments 𝗧𝗵𝗲 𝗰𝗹𝗮𝘀𝘀𝗶𝗰 𝗽𝗿𝗼𝗴𝗿𝗲𝘀𝘀𝗶𝗼𝗻: Week 1: "Our model works perfectly in sim!" Week 2: "Let's collect some real data to fine-tune." Week 3: "The real data completely contradicts what the sim taught..." Week 4: "Okay, let's collect way more real data." Month 2: "We basically need to retrain from scratch." 𝗧𝗵𝗲 𝗽𝗮𝗶𝗻𝗳𝘂𝗹 𝘁𝗿𝘂𝘁𝗵: There's no shortcut to real-world data collection for vision-based manipulation. Simulation is amazing for debugging, prototyping, safety testing, and of course to supplement your real data. But it's not a substitute for understanding how your robot actually behaves in the actual environment. 𝗪𝗵𝗮𝘁 𝘄𝗼𝗿𝗸𝘀: Use simulation strategically - for exploring edge cases, testing safety boundaries, and rapid iteration. But build your production models on real data from real environments. The teams that succeed treat simulation as a powerful tool, not a magic solution. This is why Neuracore focuses on making real-world data collection so much easier and faster. Because the physics of your actual environment can't be simulated away. 𝗪𝗼𝗿𝗹𝗱 𝗺𝗼𝗱𝗲𝗹𝘀, 𝘆𝗼𝘂 𝘀𝗮𝘆? 𝗪𝗲𝗹𝗹, 𝗽𝗲𝗿𝗵𝗮𝗽𝘀 𝗺𝗼𝗿𝗲 𝗼𝗻 𝘁𝗵𝗮𝘁 𝗶𝗻 𝗮𝗻𝗼𝘁𝗵𝗲𝗿 𝗽𝗼𝘀𝘁! 𝗪𝗵𝗮𝘁'𝘀 𝗯𝗲𝗲𝗻 𝘆𝗼𝘂𝗿 𝗲𝘅𝗽𝗲𝗿𝗶𝗲𝗻𝗰𝗲 𝘄𝗶𝘁𝗵 𝘀𝗶𝗺-𝘁𝗼-𝗿𝗲𝗮𝗹 𝘁𝗿𝗮𝗻𝘀𝗳𝗲𝗿? 𝗛𝗮𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸𝗲𝗱 𝗮𝘀 𝘄𝗲𝗹𝗹 𝗮𝘀 𝗲𝘅𝗽𝗲𝗰𝘁𝗲𝗱?

𝗣𝗼𝗽𝘂𝗹𝗮𝗿 𝗼𝗽𝗶𝗻𝗶𝗼𝗻: "𝗝𝘂𝘀𝘁 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲 𝗺𝗼𝗿𝗲 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗶𝗼𝗻 𝗱𝗮𝘁𝗮." After working with many 𝗿𝗼𝗯𝗼𝘁 𝗺𝗮𝗻𝗶𝗽𝘂𝗹𝗮𝘁𝗶𝗼𝗻 teams who've fallen into the simulation trap, here's what I've learned: Simulation teaches your robot to be really, really good at simulation. Unlike blind locomotion policies that can get away with sim-to-real transfer because they rely mainly on proprioception and contact forces, 𝘃𝗶𝘀𝗶𝗼𝗻-𝗴𝘂𝗶𝗱𝗲𝗱 𝗺𝗮𝗻𝗶𝗽𝘂𝗹𝗮𝘁𝗶𝗼𝗻 𝗶𝘀 𝗲𝘅𝘁𝗿𝗲𝗺𝗲𝗹𝘆 𝘀𝗲𝗻𝘀𝗶𝘁𝗶𝘃𝗲 𝘁𝗼 𝘃𝗶𝘀𝘂𝗮𝗹 𝗱𝗼𝗺𝗮𝗶𝗻 𝗴𝗮𝗽. The subtle differences accumulate: - Simulated friction vs real surface textures - Perfect lighting vs shadows, reflections, glare - Ideal object geometries vs manufacturing tolerances - Instantaneous sensor readings vs real-world noise and latency - Clean backgrounds vs cluttered, dynamic environments 𝗧𝗵𝗲 𝗰𝗹𝗮𝘀𝘀𝗶𝗰 𝗽𝗿𝗼𝗴𝗿𝗲𝘀𝘀𝗶𝗼𝗻: Week 1: "Our model works perfectly in sim!" Week 2: "Let's collect some real data to fine-tune." Week 3: "The real data completely contradicts what the sim taught..." Week 4: "Okay, let's collect way more real data." Month 2: "We basically need to retrain from scratch." 𝗧𝗵𝗲 𝗽𝗮𝗶𝗻𝗳𝘂𝗹 𝘁𝗿𝘂𝘁𝗵: There's no shortcut to real-world data collection for vision-based manipulation. Simulation is amazing for debugging, prototyping, safety testing, and of course to supplement your real data. But it's not a substitute for understanding how your robot actually behaves in the actual environment. 𝗪𝗵𝗮𝘁 𝘄𝗼𝗿𝗸𝘀: Use simulation strategically - for exploring edge cases, testing safety boundaries, and rapid iteration. But build your production models on real data from real environments. The teams that succeed treat simulation as a powerful tool, not a magic solution. This is why Neuracore focuses on making real-world data collection so much easier and faster. Because the physics of your actual environment can't be simulated away. 𝗪𝗼𝗿𝗹𝗱 𝗺𝗼𝗱𝗲𝗹𝘀, 𝘆𝗼𝘂 𝘀𝗮𝘆? 𝗪𝗲𝗹𝗹, 𝗽𝗲𝗿𝗵𝗮𝗽𝘀 𝗺𝗼𝗿𝗲 𝗼𝗻 𝘁𝗵𝗮𝘁 𝗶𝗻 𝗮𝗻𝗼𝘁𝗵𝗲𝗿 𝗽𝗼𝘀𝘁! 𝗪𝗵𝗮𝘁'𝘀 𝗯𝗲𝗲𝗻 𝘆𝗼𝘂𝗿 𝗲𝘅𝗽𝗲𝗿𝗶𝗲𝗻𝗰𝗲 𝘄𝗶𝘁𝗵 𝘀𝗶𝗺-𝘁𝗼-𝗿𝗲𝗮𝗹 𝘁𝗿𝗮𝗻𝘀𝗳𝗲𝗿? 𝗛𝗮𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸𝗲𝗱 𝗮𝘀 𝘄𝗲𝗹𝗹 𝗮𝘀 𝗲𝘅𝗽𝗲𝗰𝘁𝗲𝗱?

Stephen James

31,009 görüntüleme • 1 yıl önce

We rebuilt Kiyotaka for v4.0. Still 100% free to use for all chart enjoyers. This is the biggest product release we’ve shipped yet: a complete redesign, major UI/UX upgrades, new search, new chart types, better tooling, faster performance, new color themes, and a much improved execution interface. With more coming next week. But v4 is bigger than a feature drop. Kiyotaka now feels faster, clearer, and much more intentional to use. This marks a major turning point in how Kiyotaka works and where it’s going next.

We rebuilt Kiyotaka for v4.0. Still 100% free to use for all chart enjoyers. This is the biggest product release we’ve shipped yet: a complete redesign, major UI/UX upgrades, new search, new chart types, better tooling, faster performance, new color themes, and a much improved execution interface. With more coming next week. But v4 is bigger than a feature drop. Kiyotaka now feels faster, clearer, and much more intentional to use. This marks a major turning point in how Kiyotaka works and where it’s going next.

OpenMarket

39,095 görüntüleme • 4 ay önce