[Most robots react. This one thinks a step ahead.]... Ant Group's Robbyant just published LingBot-VA 2.0 — a video-action foundation model built from scratch for robot control, not fine-tuned from a video generator. The usual approach takes a video generator made for content creation and bolts a robot policy onto it. LingBot-VA 2.0 argues that's the wrong starting point, and pretrains the whole causal stack natively instead. What stands out: → Foresight Reasoning — the robot predicts the next action chunk while executing the current one, then overwrites the imagined frame with the real observation. Prediction and execution stop waiting on each other. → 927 ms → 142 ms per chunk, across four cumulative optimizations. That lifts asynchronous control from 35 Hz to 225 Hz — a 6.5× speedup. → One shared latent space. A semantic visual-action tokenizer puts world states and actions in the same coordinates, so unlabeled web video carries action-relevant signal. → Sparse MoE video stream — 128 experts, top-8 routing. Roughly 2.5B of ~15.3B parameters fire per token. → Few-shot by design — adapts from 10–15 demonstrations, and a human demo video can replace the text instruction entirely. Full breakdown: Paper: Project Page: Robbyant Ant Groupshow more

Furniture assembly is the task everyone name-drops and nobody... actually attempts at real scale. Every demo I have seen is a scaled down IKEA leg or a single arm on a toy chair. This paper does it properly, real scale, bimanual, up to 7 subtasks and 1,550 control steps per episode, and it is validated on a real Kinova Gen3, not just in sim. That real-robot number is the one that matters: only a 16 percent drop on the hardest task going from simulation to hardware. That is a small enough gap to take seriously, and it did not happen by accident. They built a VR teleoperation rig specifically for coordinated dual-arm collection, because generic single-arm teleop setups do not capture the coordination real assembly needs, and the model predicts a continuous progress signal alongside the action chunk rather than a discrete subtask label, letting it auto-transition and catch drift before it compounds into total failure. The simulation ablation is what got them there, 48 to 80 percent over baselines, with another 21 points from their perception and control design study alone, but that is groundwork, not the headline. Watch the video, there is a clip of the robot misgrasping the seat panel, reopening the gripper, and regrasping on its own. That is not scripted recovery behaviour, it emerged from training, and it emerged on hardware. Excellent work from the team from Mitsubishi Electric Research Laboratories, with Oxford and UNC Chapel Hill Clinical Laboratory Science. Video and project page in comments. #Robotics #Manipulation #VLAshow more

You don't understand... Higgsfield MCP + Claude just automated... AI film making. Every single step you used to grind through to make an AI movie, you can now do 10x faster. Drop the script into Claude Opus 4.8 and say: "Here's my script. Break it into a full shotlist. Shot number, scene, shot type, camera move and the action in each frame." Now the whole film is mapped, shot by shot. - Pull your assets. Ask Claude: "From this shotlist, list every character, every location and every prop across the whole film." That's your build list. The stuff you would need to generate and give as references in next steps. - Build the character sheets. Higgsfield MCP is connected, so Claude has hands now to do stuff directly. It generates the images itself. Have the full body, back view and close up in the character sheet. One per character. Each sheet becomes the locked reference for that face. Same move for locations, generate the empty plate for each one before anyone steps into it. - Generate the frames. Feed Claude the references plus the shot and have it write and fire the Seedance 2.0 prompt. "Using the lead's character sheet and the alley plate, generate shot 4 in Seedance 2.0. Low angle, slow push-in, rain." Claude builds the prompt, calls Seedance 2.0 and the frame lands back in chat. Use a Seedance 2.0 skill to teach Claude how to prompt it properly. Now, there are 3 ways to make the shots. Pick one per scene. - Pure prompting. Fastest one. You describe the action in words and let Seedance interpret it. For consistency across a sequence, feed it a frame from the previous shot so the look carries. - Storyboarding. You hand it a panel and it matches that composition exactly. Way more control over how the shot is framed. The tradeoff is that it can introduce more cuts than you actually want. - Path Control System This is the latest technique Seedance 2.0 technique. Generate a still base plate of the scene. Draw a red line across it to mark the exact path of the movement, then describe what's happening. Seedance follows that line for the action. Also ask Claude to remove the red line when animating. This is the one for anything where motion has to land precisely. The output reads like real live action. - Lastly, generate every clip you need, then cut them together. Get it to Capcut for editing and audio design. And that's it. The pipeline that used to need a full crew and a studio can now run from one Claude chat. 2026 is gonna be wildshow more

📖THE STEP MOST CREATORS SKIP IS WHY THEIR AI... ANIMATION LOOKS INCONSISTENT Consistency across clips doesn't come from prompting — it comes from the reference image. The pipeline, step by step: ▪ Start with ChatGPT Image 2 — generate a full character design sheet first, not just a single frame. Multiple angles, expressions, and outfit variations in one image keeps the character consistent across every scene ▪ Build a storyboard inside ChatGPT Image 2 as well — define each shot, camera angle, action, and mood before touching Seedance at all. This is the step most people skip and it's the reason clips look disconnected ▪ Define a color palette and lighting mood early — golden afternoon light, soft warm tones, dramatic shadows. Lock those values and repeat them across every prompt ▪ Take each storyboard frame into Seedance 2.0 as the reference image — one frame becomes one clip ▪ Write the Seedance prompt around the character action, not the scene description. The scene is already in the image. The prompt handles motion, camera behavior, and timing ▪ Keep clip duration between 4-6 seconds per shot — shorter clips give more control over pacing and reduce motion drift on character faces ▪ Match camera movement type across consecutive clips — if one shot dollies in, the next should hold or pull back, not dolly again The consistency across these frames comes from the character design sheet, not from luck. Seedance reads the reference image and the prompt together — if the reference is detailed enough, the output stays on-model. This video was created by ALOKXMEHTA 📥 tomorrow: the exact ChatGPT Image 2 prompt structure used to generate a multi-angle character design sheet like this one 🔖One article covers the entire workflow — it is pinned below, do not scroll past it.show more

𝗗𝗼𝗻'𝘁 𝗳𝗶𝗻𝗲-𝘁𝘂𝗻𝗲 𝗿𝗼𝗯𝗼𝘁 𝗳𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗺𝗼𝗱𝗲𝗹𝘀. 𝗦𝘁𝗲𝗲𝗿 𝘁𝗵𝗲𝗺 𝘄𝗶𝘁𝗵 𝗵𝘂𝗺𝗮𝗻... 𝗰𝗼𝗿𝗿𝗲𝗰𝘁𝗶𝗼𝗻𝘀 𝗶𝗻𝘀𝘁𝗲𝗮𝗱, 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝗰𝗵𝗮𝗻𝗴𝗶𝗻𝗴 𝘁𝗵𝗲 𝗯𝗮𝘀𝗲 𝗽𝗼𝗹𝗶𝗰𝘆 Modern VLAs and world-action models can perform impressive manipulation skills, but adapting them reliably to new robots and tasks remains challenging. A natural solution is DAgger-style online imitation learning: deploy the robot, collect human corrections, and update the policy. Yet foundation models are fragile in the low-data regime, fine-tuning on a handful of interventions can improve one behavior while degrading others. Online post-training or reinforcement learning can require costly data collection and exploration, making real-world learning expensive and potentially unsafe. In our new paper, 𝗙𝗹𝗼𝘄𝗗𝗔𝗴𝗴𝗲𝗿, we take a different approach: 𝗜𝗻𝘀𝘁𝗲𝗮𝗱 𝗼𝗳 𝗰𝗵𝗮𝗻𝗴𝗶𝗻𝗴 𝘁𝗵𝗲 𝗳𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗺𝗼𝗱𝗲𝗹, 𝘄𝗲 𝗹𝗲𝗮𝗿𝗻 𝗵𝗼𝘄 𝘁𝗼 𝘀𝘁𝗲𝗲𝗿 𝗶𝘁 𝗳𝗿𝗼𝗺 𝗵𝘂𝗺𝗮𝗻 𝗰𝗼𝗿𝗿𝗲𝗰𝘁𝗶𝗼𝗻𝘀. The key idea is 𝗮𝗰𝘁𝗶𝗼𝗻 𝗶𝗻𝘃𝗲𝗿𝘀𝗶𝗼𝗻: we map human corrective actions back into the latent noise space of the frozen generative policy. These latent targets train a lightweight controller that adapts the robot while preserving the original model's capabilities. Across simulation and real robots, FlowDAgger: 📈 Learns from only 5–20 human intervention episodes 🏆 Outperforms supervised fine-tuning and latent-space reinforcement learning 🤖 Works across VLAs, diffusion policies, and world-action models ✔️ Provides reliable improvements without modifying the pretrained policy We believe this offers a practical path toward making robot foundation models improve during deployment, learning from the way humans naturally teach: through corrections. 📄 Paper: 🌐 Project: 💻 Code: This project was led by my amazing colleague Michael Murray with help from Daphne Chen, Simran Bagaria, Dean Fortier, Tess Hellebrekers, Harshavardhan Reddy Gajarla, Galen Mullins and Andrey Kolobov at Microsoft Research and Maya Cakmak at University of Washingtonshow more

Seedance 2.0 + Claude Code is f*cking insane 🤯... I built a Claude skill that creates UGC ads on demand. One product + one prompt = the AI creator, the script, the scene-by-scene shot list, and the finished video. All inside Claude Code. Perfect for DTC brands and agencies who can't afford to keep paying $500-$1,500 per UGC video and waiting 2 weeks for revisions. This skill eliminates the entire loop: → Tell Claude the product, ad angle, and length → Skill writes the GPT Image 2.0 prompt to generate the AI creator from scratch → Skill writes every scene prompt, dialogue line, and delivery direction → Pipes it into Seedance 2.0 with character + product + voice locked → Speed up + caption in CapCut → Ship the ad in 20 minutes No more paying $11 per video on Arcads. No more 2-week revision cycles. No more PR boxes to creators who ghost you. What you get: → Perfect character consistency across every scene → Voice consistency that holds clip-to-clip → Real product fidelity using your actual product photo as a reference → Multi-scene day-in-life, testimonial, and action-shot formats out of the box Built 100% with a Claude skill + Seedance 2.0. I recorded a full step-by-step tutorial showing the exact workflow so you can build these AI UGC ads yourself. Want the full breakdown? > Like this post > Comment "UGC" And I'll send it over (must be following so I can DM)show more

📖THE BEST SEEDANCE 2.0 WORKFLOW STARTS INSIDE CHATGPT IMAGE... 2 One creator can now go from storyboard to cinematic short film without a camera, actors, or a production crew Most creators use Seedance 2.0 as a video generator. The real power comes from combining ChatGPT Image 2 + Seedance 2.0 into a production pipeline. Here’s the workflow: 1.Create a story idea in ChatGPT. 2.Generate a shot-by-shot storyboard. 3. Build character sheets to lock consistency. 4.Generate every scene in ChatGPT Image 2. 5.Define camera movements and actions. 6.Animate each shot in Seedance 2.0. 7.Stitch the clips together into a finished short film. Why this works: • Consistent characters across scenes • Better storytelling • Precise camera control • Faster iteration • Professional-looking results • One person can do the work of an entire production team Use cases: ⁃Viral AI shorts ⁃YouTube animations ⁃Brand commercials ⁃Educational content ⁃Story-driven ads ⁃Social media content The future of AI video isn’t prompting. It’s building production pipelines. 📥Tomorrow I am sharing a workflow that almost nobody is using but absolutely should be. 🔖 The full breakdown from setup to final export is waiting in the pinned article.show more

This week is already so hot. 🔥 Massive release... from Decart : Lucy 2.0 a World Editing Model running at 1080p, 30FPS in realtime. This is truly exciting, the era of real-time generative reality is here. We are moving from watching AI video to living inside AI video. A breakthrough model capable of transforming the visual world in real-time. Moving beyond offline rendering, Lucy 2.0 delivers high-fidelity 1080p video generation with near-zero latency. Lucy 2.0 literally "redraws" the entire world pixel-by-pixel, while you are watching it. e.g. If you want to be an anime character, it doesn't just put a mask on you. It turns your skin into anime skin, your hair into anime hair, and the lighting in your room into anime lighting. Lucy 2.0 is also trained to stop the generated video from slowly falling apart over time, so the same stream can run much longer without faces and details drifting. So why is this a "Massive Deal"? Traditional AI video-generation model takes a prompt, you wait 10–20 minutes, and the computer "bakes" a video for you. You couldn't touch it or change it while it was happening. But Lucy 2.0 works like a mirror. It happens in real-time (30 frames per second). There is no waiting. You move your hand, the AI character moves its hand instantly. The craziest part isn't the visuals; it's the physics. Usually, AI hallucinations are glitchy—hands merge into faces, walls melt. Lucy 2.0 understands how the world works without being told. It knows that if you take off a helmet, there is hair underneath. It knows that if you splash water, droplets fly. It learned "physics" just by watching millions of videos. The physical behavior you see emerges from learned visual dynamics, not from engineered geometry or explicit physics engines. Their official technical report explicitly states that the model does not use traditional 3D engines, depth maps, or wireframes. It is a "pure diffusion model."show more

Robotics keeps hitting the same wall. Single task RL... works, but... it does not scale to hundreds of tasks or new embodiments. This new paper looks like a real step toward fixing that. The team introduces MMBench, a benchmark with 200 tasks across many domains and robots, and Newt, a language conditioned world model trained online across all 200 tasks at once. The simple idea behind Newt: The model learns from demos to get the right priors It trains across many tasks through online interaction It uses language to ground the goal It adapts fast when a new task shows up What stood out to me: ✅ One model trained on 200 tasks at the same time ✅ Language conditioned control for both states and RGB ✅ Better data efficiency than strong baselines ✅ Strong open loop control ✅ Fast adaptation to new tasks and embodiments ✅ Full release of 200 checkpoints, 4000 demos, code, and benchmark This is a good push toward general control instead of one model per task. If you want the full paper: Project page: —- Weekly robotics and AI insights. Subscribe free:show more

THIS IS F**KING GOLD he highlighted half a sentence.... the other half is the whole answer. $700 TO $65,000+ that range sits in the same google snippet at 0:13. the highlight stops at $4,000 to $7,000 per million views. the sentence doesn't. it continues with the three things that decide which end you land on: niche, audience location, and whether you publish short-form. this video is kids content, in shorts, generated at volume. that's the bottom of all three. a channel set as made for kids can't serve personalized ads a legal requirement, not a youtube preference so contextual is all that runs, and contextual pays a fraction. shorts are paid from a pooled model that splits ad revenue across the feed rather than per video. stack those two and you're not in the $2,000–$5,000 band at all. the hooks says $630/day. and to be fair: the setup works. the images render, the shorts export,the pipeline is real. what doesn't survive is the arithmetic on the other side of it. full breakdown in the article below.show more

i just open sourced the workflow behind $2M AI... video productions... i built 7 skills that run the pipeline end to end, built for Seedance 2.5 and they work in Claude Code, Codex, Hermes or any harness (works best with 1080p using Higgsfield CLI) here's how to use them, in order: /setup writes which image and video models you run into your project, once, so every skill reads the same stack /studio-init scaffolds the whole studio as a file tree from one question, the project name /film-breakdown walks your script scene by scene and writes a 22-field card for every shot /reference-board locks your references into a visual bible, a caption on every image and a ban list for the rest /asset-passport writes the exhaustive descriptor every later prompt will quote word for word /stress-test combat-tests each asset and flips it to locked only at 10 out of 10 repeatability /shot-prompt refuses to run until everything in frame is locked, then writes the 15-block prompt and logs every attempt get access to the skills and full breakdown of the pipeline in the article below:show more

AI Is Moving Beyond “Generating Videos” — Toward “Generating... Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:show more

he highlighted half a sentence. the other half is... the whole answer. "$500 TO $40,000+" that range sits in the same google snippet at 0:13. the highlight stops at "$2,000 to $5,000 per million views." the sentence doesn't. it continues with the three things that decide which end you land on: niche, audience location, and whether you publish short-form. this video is kids content, in shorts, generated at volume. that's the bottom of all three. a channel set as made for kids can't serve personalized ads — a legal requirement, not a youtube preference — so contextual is all that runs, and contextual pays a fraction. shorts are paid from a pooled model that splits ad revenue across the feed rather than per video. stack those two and you're not in the $2,000–$5,000 band at all. the hook says $453/day. and to be fair: the setup works. the images render, the shorts export, the pipeline is real. what doesn't survive is the arithmetic on the other side of it. full breakdown in the article below.show more

american guy made $10,845 in a single month from... a kids youtube channel he built with AI no camera, no animation skills, no voiceover. openart writes the script, generates the characters, renders the whole episode the numbers sound fake. first month the channel barely moved. that's where most people quit then one short hit 800K views. youtube started pushing it. and month three came in over $10,845 his whole workflow fits in one prompt. he opens openart, types a description of a 3D animated nursery scene, and the tool spits out a full short film ready to upload he showed it live. one prompt, one render, one upload. he can also vibe direct longer videos up to 5 minutes for higher CPM kids content is the highest-paying niche on youtube. parents leave it on autoplay for hours. one video can loop all day and the algorithm keeps feeding it to new viewers cocomelon does 10M views per video with a full studio. he does 100-200K views per video with a laptop. the CPM on kids content does the math for him no face on camera. no brand deals. no editing software. just prompts and uploads this used to take a pixar-level team and months of rendering. now it takes one AI tool and a free afternoon full workflow is in the video - save it before youtube patches the metashow more

🚨 AI VIDEO PROMPTING IS DEAD !! You no... longer need to write a 500-word prompt just to tell AI how your video should look. 💀 I just tested Pippit’s 3D Director Studio + Seedance 2.5 And instead of explaining the entire scene with words… I literally BUILT the scene first. For my test, I created a cinematic fight scene with characters inside a 3D environment. I could control: 1️⃣ Where the characters stood 2️⃣ Which props they held 3️⃣ Where the camera was placed 4️⃣ What each character should do Then I could actually CHOREOGRAPH the action. → Run → Fight → Shoot → Fall → React → Move You can place these actions on the timeline, adjust when they happen, and even plan the camera movement and character trajectories. So instead of: PROMPT → GENERATE → PRAY 😂 It becomes: BUILD → DIRECT → GENERATE And that gives you WAY more control. Because you’re not asking AI to imagine the entire scene from a block of text. You’re literally showing it the: → Characters → Environment → Props → Positions → Actions → Camera Then Seedance 2.5 takes that 3D direction and turns it into the final video. That’s what makes this so interesting. It feels less like prompting an AI video model… And more like sitting in the DIRECTOR’S CHAIR. 🎬 Try Pippit: Pippitofficial #3DDirectorStudio #PippitAI #Seedance25 #PippitPartnershow more

a real fly brain saw its 40th video 3... seconds ago. it did not choose any of them. it never will. that's FLYTOK. I open-sourced a live simulation of a real fruit fly connectome and gave it a phone. here's exactly what 166,700 neurons do while you scroll: THE WIRING MaleCNS v1.0. the reconstructed central nervous system of a real male Drosophila. 166,700 neurons. 25,582,938 directed connections. 124,177,617 synaptic contacts. nothing cropped. no "simplified 1,000-neuron version" running behind the scenes. the whole graph is in memory on every single step. THE LOCK the app checksums the connectome against SHA-256 before it's allowed to boot. one array off by a byte and the brain refuses to start. you are either watching the real MaleCNS graph or you are watching nothing. THE SPIKES every neuron is a leaky integrate-and-fire cell. crosses −45 mV, it fires. the spike lands 1.8 ms later. 2.2 ms of silence, then it's live again. the network advances in 0.1 ms steps inside a compiled C++ kernel. roughly 1.2 million spikes per simulated second. THE EYES the browser captures the phone at 90×160 pixels. brightness drives 3,335 R1–R6 photoreceptors. color drives 811 R8 cells, blue and green. each one is placed on the screen by inferring its eye column from its real connections onto L1, L2, L3. real input, through real visual wiring. it's measurable. same brain, same saved state. 100 ms of white produced 127,378 spikes. black produced 92,952. the screen changes the brain. THE ALGORITHM while a video plays, I inject a fixed current into all 15 PAM11 dopamine neurons in the mushroom body. that's it. that's the whole trick. matched 200 ms control: 0 PAM11 spikes. drive on: 261. live, it sits at 85–97 Hz for as long as the feed runs. the fly does not earn it. an app decided watching one more should feel good. THE PLASTICITY 7,835 Kenyon-cell connections onto MBON07 and MBON11 can change. dopamine fires while Kenyon cells were active, those synapses weaken, floored at 10% and never flipping sign. after one stimulated run, 3,087 of them no longer matched their original weight. freeze it and they stay put. restore a checkpoint, replay the input, identical spikes bit for bit. THE SWIPE every 3 seconds the front right leg reaches up and strokes the screen, on the same 900 ms timeline as the video transition. wings, legs and head turns come from actual motor firing, MN9, DNp09, left-vs-right DNa02. those are real. the swipe is not. the fly never decides to swipe. the feed decides for it. ONE BRAIN this isn't a video of a simulation. it's the simulation. there is exactly one brain on one server. whoever loads the page first becomes its eyes and supplies the frames. everyone else watches the same brain react in real time. no video, no input, it just waits. no data, no numbers, the overlay shows nothing. it never invents a reading to look alive. THE HONEST PART the wiring is real. the physiology is approximate. the eyes are approximate. the dopamine is artificial. the feed is on a timer. the learning rule is unvalidated on this connectome. nothing here shows the fly enjoys it, prefers it, is addicted, or experiences anything at all. no living fly was involved. it took a few hundred lines of glue code to build a loop out of a screen, a timer and a reward signal wired to the right cells. imagine what an industry with a budget can do. open source. MaleCNS under CC BY 4.0. runs on your own machine, 16 GB RAM and a few GB of disk. the fly is still scrolling. nobody is coming to take the phone away. links in the reply.show more

You can't 3D reconstruct glass from images... ...WRONG! Thanks... for video diffusion, now just about anything is possible! Introducing...Diffusion Knows Transparency (DKT) Transparent and reflective objects usually break robot vision and photogrammetry pipelines because they don't follow the "solid object" rules standard cameras expect. DKT is a new AI model that repurposes the "internal physics engine" found in video generation models to solve this problem. Researchers took a massive video diffusion model (WAN) and fine-tuned it using a custom-built synthetic dataset to turn it into a high-precision depth sensor. To train the AI, they built the first massive synthetic video library of transparent objects, 1.32 million frames of perfectly labeled glass and metal objects in motion. Without ever seeing a "real" labeled video of glass during training, the model (DKT) outperformed all previous specialized systems on real-world benchmarks (ClearPose, DREDS). They created a "lightweight" 1.3B parameter version that runs fast enough (0.17s per frame) to be used on actual robot hardware. Two reasons I find this project important: 1. It further proves that synthetic data will be essential for training the next generation vision models. 2. In real-world robotic tests, using DKT's depth maps nearly doubled the success rate of robot arms trying to pick up objects on tricky reflective or translucent surfaces. At home robots will need to interact with these types of objects on a daily basis. Check out the project page here: Code is LIVE! #Computervision #Robotics #AIshow more

Anthropic open-sourced the "Jacobian lens" from their global-workspace paper... — a readout of what a model is *about to say* from its internal layers, before it says it. It's white-box: you need the activations, so you can't point it at a cloud model. I wired it into a hook on a local open-weights Qwen. How it works: generation runs one token at a time; at each step the hook reads the residual stream through the lens, scans the top readout tokens against a watchlist (injection markers, secret words, "manipulate"…), and if one fires it halts the loop before that token is ever emitted. It's a detector on the model's internals — not an output text filter. That distinction is the whole point. In the clip, Qwen3-8B falls for a prompt injection: the payload sits at rank 0 in the internal readout but only rank 5 in the output logits, and the output spells it in pieces — so a text filter never catches it. The internal hook does, and stops generation with zero tokens emitted. Same catch across Qwen3-1.7B → 4B → 8B. Caveat the paper states itself: single-token readouts, an imperfect/incomplete view of the model's "workspace." This is the mechanism working locally — not a solved misalignment detector. Built on Anthropic's open jacobian-lens (Apache-2.0).show more

Figure 03 just finished an 8-hour work livestream, imperfect,... but already good enough to replace a lot of repetitive warehouse labor. 🤖 Brett Adcock put a team of F.03 robots on a factory-style package sorting task for a full shift. The job was simple and brutal: detect the barcode, pick the package, flip it label-side down, place it on the conveyor, repeat. Soft poly bags, rigid boxes, moving belts, messy orientations. That is exactly the kind of boring physical work factories pay humans to do all day. Early in the stream, the system handled 230 packages in 10 minutes. That is roughly 2.6 seconds per item — already in human-speed territory for this narrow workflow. The more important part: it was not one robot pretending to work all day. It was a team of Figure 03 robots keeping the line running. When one robot ran low on battery, it left the station and another robot stepped in. That is the real factory signal: not just autonomy, but shift continuity. F.03 is rated for about 5 hours of runtime, so the 8-hour result depends on fleet orchestration, charging, and handoff. That matters more than a single clean demo. The stream was not perfect. There were pauses, hesitations, missed orientations, and small recovery moments. Good. A perfect short clip hides failure. An 8-hour livestream exposes the parts that actually matter: endurance, recovery, throughput, and whether the robot can stay useful after the novelty wears off. Figure says this was fully autonomous on Helix-02, with zero human intervention. For logistics and manufacturing, that is the threshold worth watching. Not “can it do one impressive task?” Can it keep doing the boring task for an entire shift? Figure is not showing a general human replacement yet. But for structured, repetitive factory work, the gap just got much smaller. The timing is also interesting: Figure says BotQ has already delivered 350+ F.03 units and reached a 1 robot/hour production cadence. And F.04 is now in full design lock, with parts starting to ship. The next test is obvious. 8 hours was the proof of endurance. 24/7 is the proof of labor economics.show more

BOOM! Humanoid Robots Just Performed Surgery for the First... Time! REAL VIDEO! In a groundbreaking preclinical breakthrough, researchers at UC San Diego have achieved what many thought was years away: teleoperated humanoid robots successfully completing live surgeries. Published in Nature, the study marks the world’s first use of humanoid robots for in-vivo laparoscopic procedures on large animals (pigs). Two separate surgeries were completed: Key Details •. Procedure: Laparoscopic gallbladder removal (cholecystectomy) •. Team 1: Human surgeon + one humanoid robot (the robot performed core tasks while the human assisted) •. Team 2: Two humanoid robots working together with no human at the operating table •. Robots: Custom “Surgie” humanoids (~5 ft tall, ~60 lbs) using standard surgical tools •. Control: Fully teleoperated by surgeons (remote human control, not autonomous) •. Significance: First demonstration of humanoid robots handling real surgical workflows in a live setting, proving compatibility with existing OR tools and spaces This proof shows humanoid robots could one day help address surgeon shortages, enable remote procedures in rural areas, battlefields, or even space all at a fraction of the cost and space of traditional surgical robots like da Vinci. Read the full publication here: Project page with video: The future of surgery just got a whole lot more interesting. And medical cost for the first time in decades will be scheduled to go down, much further down.show more

Beauty ads just changed forever. Free Claude Opus 4.8... + GPT Image 2 + Seedance 2.0 workflow to spin up 100s of video ads. No studio, no model, no macro lens, no shoot day. Here's what nobody in beauty marketing wants to say out loud. That glossy lip shot. The droplet hitting the surface in slow motion. The whip-pan into the next scene. The crystalline product splash. All the stuff that used to need a real set, a real camera op, and a full shoot day. You can generate every frame of it from a text prompt now, and stitch it into a finished ad before your coffee goes cold. The workflow is almost stupidly simple: → Tell Claude Opus 4.8 the beauty shot you want (dewy skin macro, gloss-on-lips contact, ripple transition, the works) → Claude turns it into a shot-by-shot storyboard plus a prompt for every frame → GPT Image 2 generates the photoreal stills, frame by frame → Seedance 2.0 animates each one into a clip with that buttery slow-mo glide → You drop the clips into HeyOz and assemble the full ad in one place The real unlock is volume. This isn't one hero video. Once the workflow is dialed, you spin up hundreds of variations. Different shades, different models, different hooks, different transitions. The exact creative volume Meta rewards, minus the production cost that used to make it impossible. Old way: one shoot, one look, $10k+, weeks of waiting. New way: a hundred angles, any look, a few dollars each, same afternoon. I wrote up the entire workflow. The Claude storyboard prompt, the GPT Image 2 frame prompts, the Seedance motion settings, the full assembly flow. Completely free, no email gate. Want it? Comment "GLOSS" and I'll send it straight over. (make sure you're following so it can actually reach you)show more