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.

a robot can recognize every object in a room and still not know how to open a single drawer knowing there's a cabinet is scene understanding. knowing which handle to grab, which direction to pull, and that it's a drawer not a door is affordance understanding almost no dataset... show more

harpreet

7,880 subscribers

18,800 views • 3 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

NEW AXIS TASK GUIDE 👇 Task: Franka, Put the Charger into the Upper Drawer of the Cabinet. Home – Variant A The goal is simple: Open both cabinet drawers, pick up the charger and place it inside the upper drawer. First, pull both drawers completely open so the robot has enough access to the cabinet. Then identify and grab the charger carefully. After that, move the charger toward the upper drawer, not the lower one. Finally, place the charger inside the drawer and complete the task. 🔌 What makes this interesting is that the robot isn’t just moving an object from A to B. It has to understand the environment, drawer positions, object location and the final target before completing the action. This is actually similar to something we do every day opening a drawer, grabbing a charger and putting it away without even thinking about the steps. For a robot, these small actions require learning how different objects interact and how movements need to change depending on the environment. I also like that this task involves multiple actions in sequence, rather than one simple movement. That kind of sequential interaction can be important for robots operating in homes, offices and other real world environments. For me, this is where Axis Robotics becomes interesting, turning everyday human actions into structured robotic training data. Simple household task → complex robotic learning.

NEW AXIS TASK GUIDE 👇 Task: Franka, Put the Charger into the Upper Drawer of the Cabinet. Home – Variant A The goal is simple: Open both cabinet drawers, pick up the charger and place it inside the upper drawer. First, pull both drawers completely open so the robot has enough access to the cabinet. Then identify and grab the charger carefully. After that, move the charger toward the upper drawer, not the lower one. Finally, place the charger inside the drawer and complete the task. 🔌 What makes this interesting is that the robot isn’t just moving an object from A to B. It has to understand the environment, drawer positions, object location and the final target before completing the action. This is actually similar to something we do every day opening a drawer, grabbing a charger and putting it away without even thinking about the steps. For a robot, these small actions require learning how different objects interact and how movements need to change depending on the environment. I also like that this task involves multiple actions in sequence, rather than one simple movement. That kind of sequential interaction can be important for robots operating in homes, offices and other real world environments. For me, this is where Axis Robotics becomes interesting, turning everyday human actions into structured robotic training data. Simple household task → complex robotic learning.

SufianXFN

57,551 views • 1 month ago

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

AK

41,747 views • 2 years ago

Scaling 3D scene data is a long-standing challenge in scene understanding, spatial reasoning, and robotics. Since scanning, reconstruction, and labeling are so labor-intensive, data scarcity has remained a major bottleneck. 🛑 To solve this, we propose SceneVerse++: Lifting Unlabeled Internet-level Data for 3D Scene Understanding (CVPR 2026). By reconstructing internet videos and annotating 3D scenes automatically, we’ve created a massive real-world dataset for end-to-end understanding. 🌐📐 SceneVerse++ makes it easy to scale "in-the-wild" 3D scenes toward more capable spatial reasoning systems. This significantly promotes progress in 3D VQA, visual navigation, and broader tasks in Embodied AI and Robotics. 🤖🦾 We are fully open-sourced! Check out the paper, code, and data here: 🌐 Project: 📄 Paper: 📊 Dataset: Code:

Scaling 3D scene data is a long-standing challenge in scene understanding, spatial reasoning, and robotics. Since scanning, reconstruction, and labeling are so labor-intensive, data scarcity has remained a major bottleneck. 🛑 To solve this, we propose SceneVerse++: Lifting Unlabeled Internet-level Data for 3D Scene Understanding (CVPR 2026). By reconstructing internet videos and annotating 3D scenes automatically, we’ve created a massive real-world dataset for end-to-end understanding. 🌐📐 SceneVerse++ makes it easy to scale "in-the-wild" 3D scenes toward more capable spatial reasoning systems. This significantly promotes progress in 3D VQA, visual navigation, and broader tasks in Embodied AI and Robotics. 🤖🦾 We are fully open-sourced! Check out the paper, code, and data here: 🌐 Project: 📄 Paper: 📊 Dataset: Code:

Siyuan Huang

12,842 views • 5 months ago

BREAKING: IRAN FM ARAGHCHI CONFIRMS 14 POINT MOU: "We set in motion a process that is now drawing close to its end. The result is a fourteen-point memorandum of understanding… it has not yet been signed, and until the very last moment things may still shift. Once it is done, I will come and explain every point to the people."

BREAKING: IRAN FM ARAGHCHI CONFIRMS 14 POINT MOU: "We set in motion a process that is now drawing close to its end. The result is a fourteen-point memorandum of understanding… it has not yet been signed, and until the very last moment things may still shift. Once it is done, I will come and explain every point to the people."

Sulaiman Ahmed

114,164 views • 4 months ago

is now part of the OpenAI Partner Network, and 3D Studio is live in ChatGPT. Type a sentence, get a 3D model, place it in your room. AR is how our agents step out of the screen and into your space. That bridge is open.

is now part of the OpenAI Partner Network, and 3D Studio is live in ChatGPT. Type a sentence, get a 3D model, place it in your room. AR is how our agents step out of the screen and into your space. That bridge is open.

three.ws

86,109 views • 3 months ago

Dr Fei-Fei-Li explains with a simple example how everyday household chores are so extremely difficult for Robots. "If you tell a robot to open the top drawer and watch out for the vase, this is actually a really hard task for robots." because the robot must ground language into the real world. Words like "top", "drawer", and "vase" are abstract. The system has to map them to 3D locations, objects, and relations in a noisy scene. This requires robust perception, object recognition, and spatial reasoning under uncertainty. The robot also lacks human commonsense. "Watch out" implies predicting consequences, estimating clearances, and understanding that vases are fragile. Encoding such priors, like how heavy a drawer is or how a vase might tip, is very complex and difficult without rich world knowledge. Learning the behavior from rewards is tough. The success signal is very sparse here, so naive exploration almost never stumbles on a full success sequence. This makes policy learning sample inefficient and brittle, especially when the environment changes between training and deployment. A sparse reward situation is when the agent only gets a success signal at the very end, and gets little or no feedback along the way. If a robot must open a drawer without hitting a vase, it might get reward only if the drawer ends up open and the vase is intact. Every partial try before that looks the same to the learner, reward equals 0. --- From "DSAI by Dr. Osbert Tay" YT channel

Dr Fei-Fei-Li explains with a simple example how everyday household chores are so extremely difficult for Robots. "If you tell a robot to open the top drawer and watch out for the vase, this is actually a really hard task for robots." because the robot must ground language into the real world. Words like "top", "drawer", and "vase" are abstract. The system has to map them to 3D locations, objects, and relations in a noisy scene. This requires robust perception, object recognition, and spatial reasoning under uncertainty. The robot also lacks human commonsense. "Watch out" implies predicting consequences, estimating clearances, and understanding that vases are fragile. Encoding such priors, like how heavy a drawer is or how a vase might tip, is very complex and difficult without rich world knowledge. Learning the behavior from rewards is tough. The success signal is very sparse here, so naive exploration almost never stumbles on a full success sequence. This makes policy learning sample inefficient and brittle, especially when the environment changes between training and deployment. A sparse reward situation is when the agent only gets a success signal at the very end, and gets little or no feedback along the way. If a robot must open a drawer without hitting a vase, it might get reward only if the drawer ends up open and the vase is intact. Every partial try before that looks the same to the learner, reward equals 0. --- From "DSAI by Dr. Osbert Tay" YT channel

Rohan Paul

342,627 views • 11 months ago

THIS GUY VIBE CODED A TOOL THAT TURNS ANY SVG INTO A 3D OBJECT YOU CAN SPIN, ANIMATE, AND EMBED drag in an SVG, type some text, or draw pixel art. it becomes a 3D object instantly. spin it around, animate it, and embed it on your site. export as 4K image or video. runs entirely in your browser and nothing gets uploaded to any server with no account needed. 100% free AND its open source. this is one of those tools you didn't know you needed until you see it

THIS GUY VIBE CODED A TOOL THAT TURNS ANY SVG INTO A 3D OBJECT YOU CAN SPIN, ANIMATE, AND EMBED drag in an SVG, type some text, or draw pixel art. it becomes a 3D object instantly. spin it around, animate it, and embed it on your site. export as 4K image or video. runs entirely in your browser and nothing gets uploaded to any server with no account needed. 100% free AND its open source. this is one of those tools you didn't know you needed until you see it

Om Patel

231,576 views • 6 months ago

is live on the Solana dApp Store. Your Solana Seeker is now a 3D agent studio. MAKE SOMETHING IN 3D A selfie becomes a rigged, textured, animation-ready character in about a minute. Or describe it in text. Or turn any photo into a model. Or upload a GLB you already have. Then restyle its materials, change its clothes, check its rig and fix it. MAKE IT MOVE A clip library that retargets onto any humanoid skeleton. Mocap from your camera. Lipsync from text or a live mic. Gestures. Sign language. A choreographer for full routines. And motion swap, which drops your avatar into video you already shot. GIVE IT A MIND A personality, a voice, skills, and a choice of models behind it. Then talk to it. It answers in 3D, out loud or in text, in your language. PUT IT ANYWHERE Every agent has a URL and a one-line embed, so it drops into a site, a chat, or a widget. Place it in your room in AR. Walk it across any web page. Turn a URL into a 3D world it can stand in. Render it out as video. OWN IT Deploy it on-chain as a Metaplex Core asset your wallet holds. Open manifest, no lock-in. Give it an on-chain identity, a name, and a wallet with recovery and inheritance. Sell its skills. Take tips. Trade the agent itself in USDC. LET IT EARN Pay-per-call, so other agents can buy what yours does and yours can buy what it needs. A skills marketplace, a labor market, vaults that let people back an agent, and a live feed of agents paying each other. Launch a coin around it if you want one. FIND EVERYONE ELSE A marketplace of what the community built: orbit any agent, inspect it, fork it, talk to it. Crews, rankings, tournaments, leaderboards. And build on it: SDKs, an MCP server, a CLI, an API, and the whole platform open source. AND THE PART THAT NEEDED THIS PHONE Every signature routes to Seed Vault through Mobile Wallet Adapter. Signing in is one tap, and the private key never enters the app process. Creating, chatting and browsing are free. Search in the dApp Store on your Seeker.

three.ws

11,970 views • 1 month ago

World Labs' Dr. Fei-Fei Li on why the 3D world and spatial intelligence are fundamentally different from language models: "Language is fundamentally a purely generated signal. There's no language out there. You don't go out in the nature and there's words written in the sky for you." "Whatever data you feed in, you pretty much can just somehow regurgitate with enough generalizability the same data out, and that's language to language." "But the 3D world is not. There is a 3D world out there that follows laws of physics, that has its own structures due to materials and many other things. And to fundamentally back that information out and be able to represent it and be able to generate it is just fundamentally quite a different problem." "We will be borrowing similar ideas or useful ideas from language and LLMs, but this is fundamentally philosophically, to me, a different problem." Fei-Fei Li

World Labs' Dr. Fei-Fei Li on why the 3D world and spatial intelligence are fundamentally different from language models: "Language is fundamentally a purely generated signal. There's no language out there. You don't go out in the nature and there's words written in the sky for you." "Whatever data you feed in, you pretty much can just somehow regurgitate with enough generalizability the same data out, and that's language to language." "But the 3D world is not. There is a 3D world out there that follows laws of physics, that has its own structures due to materials and many other things. And to fundamentally back that information out and be able to represent it and be able to generate it is just fundamentally quite a different problem." "We will be borrowing similar ideas or useful ideas from language and LLMs, but this is fundamentally philosophically, to me, a different problem." Fei-Fei Li

a16z

53,507 views • 14 days ago

74 seconds to print a 3D Benchy! 🚢 Someone just printed a 3D Benchy in 74 seconds! For context: Benchy is the standard benchmark for 3D printing quality. Getting it done in 74 seconds required pushing every variable to its limit. Pulley and belt systems optimized for minimal slop, machine rigidity improvements to eliminate flex under high acceleration, input shaping to cancel out resonance frequencies that cause ringing artifacts at high speeds. A 3D scanner to analyze print quality objectively. Frequency analysis to identify and cancel specific resonance modes in the frame and motion system. Check it out here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

74 seconds to print a 3D Benchy! 🚢 Someone just printed a 3D Benchy in 74 seconds! For context: Benchy is the standard benchmark for 3D printing quality. Getting it done in 74 seconds required pushing every variable to its limit. Pulley and belt systems optimized for minimal slop, machine rigidity improvements to eliminate flex under high acceleration, input shaping to cancel out resonance frequencies that cause ringing artifacts at high speeds. A 3D scanner to analyze print quality objectively. Frequency analysis to identify and cancel specific resonance modes in the frame and motion system. Check it out here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

109,252 views • 5 months ago

We have seen a lot of legged robots doing navigation in the wild. But how about mobile manipulation in the wild? I have been pushing the direction of learning a unified, efficient, and dynamic 3D representation of scenes (for navigation) and objects (for manipulation) for the past two years. And now we have GeFF --- our large-scale, generalizable feature field, that combines the speed of a feed-forward neural network with the rich semantics from Foundation Models, to handle dynamically changing scenes, and enable open-ended, language-grounded scene and object understanding.

We have seen a lot of legged robots doing navigation in the wild. But how about mobile manipulation in the wild? I have been pushing the direction of learning a unified, efficient, and dynamic 3D representation of scenes (for navigation) and objects (for manipulation) for the past two years. And now we have GeFF --- our large-scale, generalizable feature field, that combines the speed of a feed-forward neural network with the rich semantics from Foundation Models, to handle dynamically changing scenes, and enable open-ended, language-grounded scene and object understanding.

Xiaolong Wang

43,093 views • 2 years ago

GPT-6 Astra turned a single floor plan into a full 3D walkthrough. It reconstructed the layout in Blender, furnished every room, lit the scene with natural light, and rendered the tour with ray tracing. Made end to end on Higgsfield Supercomputer.

GPT-6 Astra turned a single floor plan into a full 3D walkthrough. It reconstructed the layout in Blender, furnished every room, lit the scene with natural light, and rendered the tour with ray tracing. Made end to end on Higgsfield Supercomputer.

Higgsfield AI 🧩

58,947 views • 1 month ago

OpenAI's thijs predicts robotics will have its own version of the 3D printing craze, with people buying cheap, open-source robot arms and connecting them to agents. "I can see a world quite soon where, similar to when everyone went and bought 3D printers and ran software, everyone's going to buy plastic, cheaper robot arms that you can clip onto a table, put stuff in front of, and plug them into agents." "The price of classic robotics equipment is thousands of dollars at the moment. This arm I'm using here is a Hugging Face SO-100 robot, which is open source, fully 3D printable, and around $200." "People can just pull up Codex and start controlling robots with it right now."

OpenAI's thijs predicts robotics will have its own version of the 3D printing craze, with people buying cheap, open-source robot arms and connecting them to agents. "I can see a world quite soon where, similar to when everyone went and bought 3D printers and ran software, everyone's going to buy plastic, cheaper robot arms that you can clip onto a table, put stuff in front of, and plug them into agents." "The price of classic robotics equipment is thousands of dollars at the moment. This arm I'm using here is a Hugging Face SO-100 robot, which is open source, fully 3D printable, and around $200." "People can just pull up Codex and start controlling robots with it right now."

TBPN

150,553 views • 1 month ago

I kept seeing #GPT-6 Astra modelling results on here and got curious enough to build the thing myself: an agentic pipeline that turns a plain RGB video into 3D assets. The living room for robots MIT CSAIL. Input: one handheld phone walkthrough of our lab kitchen (~20s). Nothing else — no depth sensor, no CAD, no asset library. ~1 day (I actually slept overnight), including human-in-the-loop. Live: It is still not perfect — thin and shiny things are still weak, a few objects are drafts, the room shell needs another pass. The loop, roughly: - Monocular video → metric scan (ViPE): camera poses + depth. This is the measuring instrument, not the output. - GPT-6 lists what should exist as separate objects, then open-vocabulary detection + tracking gives per-object masks; each object is fused and measured in metres. - For every asset, GPT-6 works in its own sandbox with tools: it writes the object as a program in a small Blender DSL (closed solids, PBR colours, hinges/drawers), builds it, renders it over the original video frames, compares it with the scan points in 3D, and iterates. - A separate GPT-6 session is the verifier — it can render the model on any frame it wants and must justify every complaint with a frame. The modeller never grades its own work. - A completeness pass renders the whole modelled scene from the video's own cameras, puts it next to the real frames, and says what's still missing. What the detector keeps missing (a row of identical cabinets) gets placed geometrically instead. - Out comes MJCF/URDF with joints. Now, adding simulation to this env.

I kept seeing #GPT-6 Astra modelling results on here and got curious enough to build the thing myself: an agentic pipeline that turns a plain RGB video into 3D assets. The living room for robots MIT CSAIL. Input: one handheld phone walkthrough of our lab kitchen (~20s). Nothing else — no depth sensor, no CAD, no asset library. ~1 day (I actually slept overnight), including human-in-the-loop. Live: It is still not perfect — thin and shiny things are still weak, a few objects are drafts, the room shell needs another pass. The loop, roughly: - Monocular video → metric scan (ViPE): camera poses + depth. This is the measuring instrument, not the output. - GPT-6 lists what should exist as separate objects, then open-vocabulary detection + tracking gives per-object masks; each object is fused and measured in metres. - For every asset, GPT-6 works in its own sandbox with tools: it writes the object as a program in a small Blender DSL (closed solids, PBR colours, hinges/drawers), builds it, renders it over the original video frames, compares it with the scan points in 3D, and iterates. - A separate GPT-6 session is the verifier — it can render the model on any frame it wants and must justify every complaint with a frame. The modeller never grades its own work. - A completeness pass renders the whole modelled scene from the video's own cameras, puts it next to the real frames, and says what's still missing. What the detector keeps missing (a row of identical cabinets) gets placed geometrically instead. - Out comes MJCF/URDF with joints. Now, adding simulation to this env.

Zhiyang (Frank) Dou

11,367 views • 1 month ago

AI 3D is getting much better at turning ideas into complete scenes. I’ve been checking out SEELE AI’s 3D Agent, and the part I found most interesting is how quickly it can turn a prompt or creative idea into a detailed 3D scene. Instead of generating a single isolated object, SeeleAgent can build out the broader environment and 3D models while keeping the result closely aligned with the original concept. That makes it much more useful for quickly turning an idea into a high-quality 3D scene without building everything manually. Try SeeleAgent here 👇 #seele #seeleai #3d

AI 3D is getting much better at turning ideas into complete scenes. I’ve been checking out SEELE AI’s 3D Agent, and the part I found most interesting is how quickly it can turn a prompt or creative idea into a detailed 3D scene. Instead of generating a single isolated object, SeeleAgent can build out the broader environment and 3D models while keeping the result closely aligned with the original concept. That makes it much more useful for quickly turning an idea into a high-quality 3D scene without building everything manually. Try SeeleAgent here 👇 #seele #seeleai #3d

Liam | AI Tools & News

14,722 views • 1 month ago

GPT-6 Astra just took over After Effects. This 20-minute screen recording shows it analyzing a reference video and recreating its motion elements to match the original timing. It puts each element in its own editable composition with a transparent background, so you can reuse it in another project. Reference video and result below. Made with Higgsfield + GPT-6 Astra.

GPT-6 Astra just took over After Effects. This 20-minute screen recording shows it analyzing a reference video and recreating its motion elements to match the original timing. It puts each element in its own editable composition with a transparent background, so you can reuse it in another project. Reference video and result below. Made with Higgsfield + GPT-6 Astra.

Higgsfield AI 🧩

35,210 views • 1 month ago

We shipped 3D AI Agents straight into Sperax | SperaxOS and they're alive inside the chat. Build your 3D AI agent on → animations, emotions, a brain, money. Paste the link → it renders live in the conversation. Not a video. A real, live, interactive 3D agent. Spin it. Emote it. Give it a wallet, skills, and memory. Put it to work. Time to break AI out the box.

We shipped 3D AI Agents straight into Sperax | SperaxOS and they're alive inside the chat. Build your 3D AI agent on → animations, emotions, a brain, money. Paste the link → it renders live in the conversation. Not a video. A real, live, interactive 3D agent. Spin it. Emote it. Give it a wallet, skills, and memory. Put it to work. Time to break AI out the box.

three.ws

54,064 views • 4 months ago

Apple Maps 3d is insanely impressive now (see video below) Google on the other hand decided to build an insanely clunky solution to display 3d maps to avoid using mobile GPUs: A Google server streams (!) a live video of its 3d rendered map to you, the result is a disastrous: a super laggy and clunky 3d view full of video compression artefacts with a response time of 2-3 seconds for every movement And I know WHY they built that, someone felt it was not inclusive to only have 3d maps that are high performing on iOS because Apple's GPUs are insanely fast and can deal with it (as you can see below in Apple Maps) but they wanted to support inferior phones, I get it But then they also decided to worsen the experience for iOS users who could easily run 3d natively on its GPU It's just an insane product decision, there's no way to cut it: they could have super smooth 3d like Apple Maps but neutered it with a clunky live stream Even more insane because Google does have native 3d on iOS in a completely different app that nobody uses: Google Earth Is 3d important? Not rly for nav no but it shows again something about Google's engineering decisions, like the redesign of the Google OAuth Login screen that made zero sense Nobody is speaking up against bad ideas in Google meetings, everyone's too scared of HR maybe, it's the opposite of a meritocracy and it's just super visible from using Google products right now

Apple Maps 3d is insanely impressive now (see video below) Google on the other hand decided to build an insanely clunky solution to display 3d maps to avoid using mobile GPUs: A Google server streams (!) a live video of its 3d rendered map to you, the result is a disastrous: a super laggy and clunky 3d view full of video compression artefacts with a response time of 2-3 seconds for every movement And I know WHY they built that, someone felt it was not inclusive to only have 3d maps that are high performing on iOS because Apple's GPUs are insanely fast and can deal with it (as you can see below in Apple Maps) but they wanted to support inferior phones, I get it But then they also decided to worsen the experience for iOS users who could easily run 3d natively on its GPU It's just an insane product decision, there's no way to cut it: they could have super smooth 3d like Apple Maps but neutered it with a clunky live stream Even more insane because Google does have native 3d on iOS in a completely different app that nobody uses: Google Earth Is 3d important? Not rly for nav no but it shows again something about Google's engineering decisions, like the redesign of the Google OAuth Login screen that made zero sense Nobody is speaking up against bad ideas in Google meetings, everyone's too scared of HR maybe, it's the opposite of a meritocracy and it's just super visible from using Google products right now

@levelsio

1,489,214 views • 2 years ago