Score
@webuildscore • 9,969 subscribers
Open Vision AI for everyone. Score Studio + SN44
Shorts
Videos
Score x CARD Cricket is the world’s second-largest sport, yet advanced analysis hasn’t been widely accessible. Together with CARD, we’re bringing frontier Vision AI to the game. From talent ID and player pathways to predictive insights for clubs, franchises, and national teams.
Score - Subnet 44845,677 görüntüleme • 10 ay önce
Score x Reading FC Over the next year with Reading FC, we’ll build vision AI models that turn match footage into game changing insights for their coaches and players, and systems that make stadium operations smarter and more efficient for elite sport organisations.
Score - Subnet 44437,731 görüntüleme • 11 ay önce
Astra Ultra did not cook sports-grade vision AI. Gave it a 30s football clip from our subnet private track. Frame-level events, JSON, annotated video. Ground truth and the published scoring rules only after it committed. 22 predictions. 17 real events. 15 inside the action windows. 7 extras. 2 misses. Precision 68.18%. Recall 88.24%. F1 76.92%. Our Bittensor eval, SN44: 0%. Matches after timing decay: 16.538 False positives: −20.300 GT weight: 25.600 score = max(0, (16.538 − 20.300) / 25.600) = 0 Three extra take-ons and two extra tackles were 14.6 penalty points. It also misread the late interception/clearance. Rare actions pay more when you hit them and tax you harder when you invent them. Perfect timestamps on the matches still would not have cleared that bill. This was one offline replay of the published scorer. Unchanged preds. Not live latency. Not a season. The point is simpler than the arithmetic. F1 is what you post. SN44 is what you get paid on. Real matches, messy cameras, hard negatives, and a 30-second clock are not the same sport as a nice 15s clip to aura farm on Twitter.
Score30,911 görüntüleme • 1 ay önce
Roboflow charges you for models you have to verify yourself. Introducing Score Studio: the decentralised alternative where every model arrives already proven and ready to work in real world conditions. Every model on the platform is battle-tested through SN44's validation mechanism before you ever touch it. Miners compete, validators score, only the winners survive. You get the output of a permanent open competition, at a fraction of the price. Datasets, annotation, training, deployment. All of it cheaper. All of it validated, accurate and efficient. Need a model that doesn't exist yet? Launch your own model inquiry from the Studio and put the network to work on it. Pay in USD or SN44, straight at subnet level. We're putting the final touches on it now.
Score35,419 görüntüleme • 2 ay önce
Score Studio won't be limited to the models trained (past, present or future) on the subnet. You'll be able to run the rest of the computer vision stack in the same app. This is our quantized SAM3, used inside Score Studio, on Djokovic vs Nadal from the 2013 US Open final. Both players stay tracked for the whole point. Every step is drawn as a trail on the court. As the rally goes on, those trails build into a cluster: one map of where they ran. Two players, one of the longest rallies in the sport, held without losing either one, processed through a small, fast and efficient open-source segmentation model.
Score21,084 görüntüleme • 1 ay önce
John Wick scenes are one of the hardest to track. we ran our subnet vision models on one of them. Shot at night, barely any light. The camera whipping around, cars sliding sideways, people cutting through the gaps, all of it smeared with motion blur. this is the footage most models fall apart on. Ours held it. every car and every person detected, outlined, and tracked, each one carried under its own ID from the moment it enters frame to the moment it leaves. thousands of unique tracks across the clip, through the dark and the chaos, without losing the thread. And the model doing it is smaller than you would ever guess. no giant model, no cloud.
Score22,251 görüntüleme • 1 ay önce
No one else can do this. While every other CV platform is still selling another fine-tuning dashboard We’re about to let anyone order actual frontier lab work in a few clicks. The kind only Bittensor miners can deliver. Model Foundry is coming to Score Studio. Zero compute? Zero data? Zero ML team? Doesn’t matter. You describe the hard vision problem, our miners build the production model, you pay inside the Studio. That spend goes straight into SN44 buyback + burn. Money never leaves the subnet. No gatekeepers. No bottlenecks. Just open frontier vision for everyone. Check out the Model Foundry flow 👇
Score24,543 görüntüleme • 1 ay önce
We’re preparing the launch of Score Studio. Ad campaigns will roll out gradually, and we’ll be launching it across platforms like Product Hunt and others. This is the first version of the first video we’ll use for ads, not the final one, but we couldn’t wait to share with you what we’ve been up to. It’s also the start of a longer series of videos to support our growth strategy for this subnet-owned product. PS: It’s such a pleasure to be working with Mob Studios
Score18,703 görüntüleme • 1 ay önce
Just dropped two new tools in Score Studio today: → Real-time depth estimation + object detection on the same frame. → Background removal. Next… 3D point clouds Score Studio is going to become the go-to platform for anything vision: ✅ Auto-Data Generation ✅ Auto-Training ✅ Auto-Evals ✅ Auto-Deploy All battle-tested by miners. All powered by Bittensor.
Score16,778 görüntüleme • 2 ay önce
When we started Score, the standard computer vision tools already existed. About a million people use them every day. Most of those people are still waiting on labels, running training jobs by hand, and watching models fail once they leave the test set. Most of those people are still waiting on labels, running training jobs by hand, and watching models fail once they leave the test set. Most of those people are also still waiting on verified computer vision models, evaluated against real life conditions and ready to be deployed for them to deliver value for their teams, clients or users. Score Studio is the full computer vision path in one place. A team describes the problem. The system can generate the missing scenes, label them, train the candidates, evaluate which ones actually hold, and deploy the winner. Data, labels, training, eval, ship. One loop. If no model exists for that job yet, they can put a bounty on the subnet. Anything from a small vision brick to a full VLM. Miners compete on the task. Only the winning work comes back. Same path for software agents. Any agent can call it. Built to be fully agent-accessible. Built for the people who already do this work: computer vision engineers and the small teams around them in plants, warehouses, farms, robotics, sport, and security. And for the agents those teams will run. That is the part that changes the job. Not another training screen. The stretch that used to take a lab and a calendar, footage, boxes, versions, failed runs, a separate deploy project, sits behind one starting point. And if the network needs a new model, that request is part of the same path. We spent more than a year building it. Then we had a choice. Keep it for us, or commoditize the whole subnet and make it available 24/7, in permissionless and open-source way. And we knew we couldn't keep it for us. It had to live on Bittensor. Open source software already showed how this should work. Infrastructure should not sit inside one company. Same idea as open AI before the phrase changed meaning: inspect it, fork it, keep building. That is what SN44 is for. Open vision intelligence, powered by Bittensor. Miners do the work. Studio is how that gets monetized. Profit does not stay in a company account. It goes back into the subnet through buyback and burn. We built the tool we wanted on day one. It will live on the network now, and for ever. Waitlist is open.
Score11,292 görüntüleme • 1 ay önce
Computer vision engineers are still duct-taping tools together just to get a model into production. We just finished another round of user interviews and that frustration came up again and again. So we re-designed Studio to work around our new Pipelines + Workflow Canvas features. Visually design any vision pipeline from start to finish, connect models, logic, and outputs on one canvas, preview the exact result, then deploy. You see the output before you ship it. Everything in a single interface. The full loop, shaped by the people who actually build vision systems every day. This is what Decentralized Vision Intelligence looks like.
Score11,008 görüntüleme • 1 ay önce
$300M AUM $DKING Partnership ✅ Live at Proof of Talk, revealed the new DKING → SIRE partnership with one of the world’s largest sports-betting hedge funds. They’ll deploy $300M AUM using DKING’s DeFAI strategies, starting this 2025/26 season. $TAO Watch the moment 🔽
Score25,452 görüntüleme • 1 yıl önce
Daha fazla içerik yok.