So much of the complexity for multimodal/robotics data is... just getting the right format that's both flexible and performant. I dig into it here in the context of 3d reconstruction. I'm hoping to build an opensource arkit like pipeline and explain the first bit for the data pipeline here! Heres a video of what the final data looks like in a registered catalogshow more

Everyone is selling robotics data. Most of it isn't... what you actually need. The right kind of data depends entirely on what you're training. And that's the question almost no one asks before the check gets cut.show more

This is what it sounds like living next to... a data center. The video below was recorded at midnight, and the data center is situated next to 100s of residential homes.show more

there is so much real data just sitting in... the open right now it's almost funny. four years of starlight on every star, a NASA archive that's been free for over a decade, detectors still recording the sky tonight, and barely anyone has a net pointed at any of it. so i pointed one. this is me pulling the planet data, the data loading is the boring part. the net i built to read it, the wall it hit, and what that taught me about where AI goes next, that's the full story, and it drops tonight. the data's public, the tools are free, the box fits on a desk. what's stopping you. you can just do things anon.show more

I've been working a lot with SAM3 and the... Momentum Human Rig (MHR). I finally integrated it into the data I'm working with Rerun. The progression I've taken looks as follows SAM3 + SAM3D-body on 1. a single image 2. a set of multiple images 3. a single video 4. A multiview video capture I took inspiration from the SAM3D-body paper and built a multiview fitting optimization pipeline. This pipeline involves using the 2D keypoints from the single-view pipeline, triangulating them, and employing an L1 loss between the 2D/3D keypoints. The temporal stability isn't great, so that's the next portion I'm going to focus on. One really frustrating thing about SAM3D-body is the lack of per-joint confidence values. It makes it harder to deal with occlusions. I'm probably going to need to use a separate model, or maybe add a confidence head.show more

Here is a recreation of the World Cup final... on a desk! It fetches game data from an API and other sources, and stores it in Supabase to project it onto a desk in an immersive experience! Amazing to see what Codex and Supabase can create for us!show more

🚀 Introducing EgoExo Forge - built on top of... Rerun, Gradio, and Hugging Face hub (I’ll be in San Francisco July 21–29 — if you’re into robotics, egocentric AI, large-scale data collection, or just want to chat, DM me!) In my opinion, large-scale, diverse, and high-quality data is still the largest bottleneck for generalized robotics deployment. I believe that some version of imitation learning from human examples will be the most scalable + clean way to train humanoid robots 🤖 (similar to what Tesla did for Full Self Driving). Teleop is too expensive to collect a large enough dataset in a reasonable manner, so passive collection via egocentric (and in certain cases, exocentric) views feels like the right bet. Over the past few months, I've been trying to build out the scaffolding for this and using Rerun as my underlying infrastructure. Data being collected needs to be easily inspectable + time series and rerun provides the right tooling for this. My goal is to first build out a ground truth representative dataset from already existing open source data, generate some reasonable baselines, and then go out and collect my own data that adheres to the defined schema. 🔍 Starting with open-source datasets 1. EgoDex from Apple 2. HOCap from Nvidia and the University of Texas at Dallas 3. Assembly101 from Meta All these different datasets have different sensor configurations + annotations, so my goal with egoexo-forge is to have one consistent labeling scheme + data layout. I built a data pipeline that aligns all of the different datasets in one general schema assuming the COCO133 keypoint layout that allows for exo+ego, ego only, or exo only Since the scaffolding is already there, it becomes MUCH easier to add other datasets. So the next ones that I'll be including are HD-EPIC kitchens dataset, HOT3D, and finally my own personal iPhone + insta360 go collection method. Once I have a diverse variety of datasets, I'll double down on what I believe to be the key algorithms required to make useful data for imitation learning 📊 1. Camera Pose estimation via SLAM/SFM for ego perspective (and automatic calibration for exo) 2. Human pose estimation for both egocentric + exocentric views 3. Metric 3D reconstruction + object tracking I'll be setting up reasonable open-source baselines for each of these to validate that these datasets work, and then finally try to use the generated datasets for some imitation learning via the pi0-lerobot repo I've been working on. I plan on making a blog post + providing more info on all of this in the near future so stay tunedshow more

Cleaning up your data frame is a snap with... Data Wrangler. Drop missing values, see a diff of what will be changed and even get the generated code for the drop. Get Data Wrangler here (yes, it's free):show more

Package a project for a futuristic city in the... middle of the desert, fool the public that it is for the future, gather more than $500 billion, and then scale it back to data centers and a survival city for the elites. The Line is not canceled; it's scaled down like it was always intended. They will pour trillions of dollars into the data centers and a 3-mile-long doomsday bunker protected by 500-meter walls and an entire ecosystem because the outside weather and cosmic radiation will be terrible.show more

🚀 My New Book is Here: Data Strategy (3rd... Edition) 🚀 I’m thrilled to share the release of my latest bestselling book, Data Strategy: How to Use Data and Artificial Intelligence to Transform Your Business. Every business today needs data to survive - but simply having data is not enough. What matters is how you use it. A well-designed data strategy is the key to unlocking value, driving insights, and giving your organisation the competitive edge it needs to thrive in the digital economy. From small organisations to global enterprises, I’ve seen first-hand how a data-driven approach can transform operations, improve decision-making, and unlock entirely new opportunities. That’s why I’ve poured my experience into this book — to help leaders and teams build strategies that don’t just talk about data, but actually deliver measurable impact. 🔍 In this third edition, I’ve expanded the book to reflect the latest developments in data and AI, including: ✅ Generative AI and its role in shaping business innovation. ✅ Synthetic data and how it can accelerate AI adoption. ✅ The potential of quantum computing and what it means for the future of data. ✅ Expanded guidance on cybersecurity, regulations, and ethics in a data-driven world. This isn’t just a theoretical framework - it’s a practical guide to collecting, managing, and using data effectively in order to drive growth, innovation, and long-term success. Whether you’re leading a start-up or a multinational, Data Strategy will equip you with the tools you need to stay ahead in a rapidly evolving landscape. 📖 Pre-order your copy today: 👉 Amazon - 👉 Kogan Page - I can’t wait to hear how this book helps you craft your own data-driven strategy and transform your business for the future.show more

What was a complex hacky pipeline in 2023 to... take indoor 3d scans and reskin them to different types of decor is now just a few clicks in 2025. World labs marble has collapsed a lot of the complexity involved in generating and editing 3d worlds:show more

A Letter to Our Community: The Road Ahead for... Robotics To our Community and Partners, As we step into 2026, our mission at Axis is clearer than ever: Constructing the definitive End-to-End Scaling Layer for Robotics. Our goal is to accelerate the transfer of diverse human intelligence into Robotics General Intelligence (RGI). By owning the critical path of intelligence creation, we are turning the physical limitations of robotics into a scalable, software-driven future. Here is our strategic outlook and roadmap for the year ahead. The Core Thesis: Simulation is the Only Way Out The path to RGI is currently blocked by Data Scarcity, Generalization Fragility, and Hardware Fragmentation. At Axis, we believe Simulation is the only way out. Our Simulation Data Platform and Data Augmentation Engine transform raw data into "Synthetic Gold". Backed by academic milestones like Roboverse, Skill Blending, and GraspVLA, we have proven that pure simulation can achieve the generalization required for the real world. We don’t just collect data; we architect it. The Engine: Why Crypto? We believe RGI should come from all, not a few. Crypto is not just a feature; it is the primitive that powers our entire ecosystem flywheel: - Incentive Mechanism: Democratizing contribution and rewarding the trainers and developers. - Assetization: Turning proprietary data and refined models into liquid, ownable assets. - Verifiable Workflow: We are opening the "Black Box" of AI. By bringing total transparency to the Task Generation → Data Collection → Model Training pipeline, we ensure every byte of intelligence is verifiable, traceable, and secure. 2026 Strategic Deliverables This year, we are committed to delivering three foundational pillars: - The World's Largest Training Dataset for Robots: A robot training set—diverse, high-quality interaction data at an unprecedented scale. - A Robotics Foundation Model: A universal robotic brain trained on our pure simulation and synthetic data, capable of robust cross-embodiment transfer and open-world adaptability. - Evolvable Robot Hardware: Robots deployed with Axis models that autonomously evolve through continuous interaction, turning every deployment into a self-improving node within our RGI network. The Ultimate Vision We are building more than models; we are architecting the Distributed Machine Economy. A future where every dataset, model, and robotic embodiment is a verifiable asset in a global, autonomous network. Thank you for building the future of intelligence with us✌️📷show more

Rise is live. The developer SDK for Phoenix Perpetuals... is here, in TypeScript and Rust. Build a trading bot. Power perps inside your existing product. Plug into live market data and trader state. One ergonomic surface for all of it.show more

Some updates on the multiview vistadream pipeline with Rerun!... Rerun came in extremely useful here, as being able to visualize depths at each stage of the pipeline allowed me to debug some nasty bugs. Since the last time, I was only working with a single image input. I've added in VGGT as my multiview pose + depth estimator. It works REALLY well for getting camera poses, but the depths are not that great. To try and fix that, I estimated depth maps from MoGeV2 for each of the views, and scale+shift aligned them so that they would match up to the confident sections of VGGT's depth predictions. You can see in the video just how much sharper the visualized 2d depth maps are! The biggest issue continues to be the multiview consistency 🫠 That's up next, along with actually training the Gaussian splat. Lots of work went into actually understanding inputs+outputs for VGGT. I had some funky bugs where the confidence values would all collapse to true I'm also really excited for this pipeline to use Difix3D+ Nvidia instead of Flux Inpainting, it seems like a better suited for a multiview pipeline.show more

The influence of set-piece coaches in the Premier League... seems to have grown significantly in recent years, but how much of an impact have they had, and is it just a fad? Here, our new-look interactive article analyses the data behind Premier League set-pieces.show more

Joined the ongoing AIOZ AI Pneumonia Chest X-Ray Classification... Challenge? Smart Tip: Focus on data quality before tuning your model. → Audit the X-rays first for variations in brightness, contrast, and resolution. → Apply preprocessing techniques such as normalization, resizing, and histogram equalization. → Add controlled data augmentation, such as rotations, flips, and subtle distortions, to improve robustness without losing clinical signals. Build a stronger pipeline from the data up! Join the challenge and explore medical AI in practice.show more

A new look for the new era of data... movement Over the past 12+ months we've been focused on building out mump2p, our Ethereum data propagation product, onboarding top validators to test it with, and educating our peers on the merits of decentralized coding. Now with the launch of mump2p on Ethereum mainnet firmly in our sights, it feels like the right time to give Optimum's visual identity a refresh-- something to match the sleek, powerful data acceleration network we're deploying. The advent of RLNC powered data movement frees blockchains from the networking bottleneck, so they can perform at the pace demanded by our ever-expanding digital economy. The new era begins soon with data propagation on Ethereum, more chains and use cases to follow. Time to raise the ceiling for blockchains, and do it in style.show more

Spent the past few weeks building a fully automated... pipeline for egocentric manipulation data with Kyle Jiang. Any new manipulation task captured using our own wearable sensing platform can now be dropped into the same pipeline with minimal manual fix. Instead of raw videos and annotations, we transform human demonstrations into robot-ready training data. Next, we're bringing touch into the loop with tactile gloves.show more

🆕 CrowdStrike is acquiring Onum to supercharge autonomous cybersecurity... with real-time data pipelines. If Falcon SIEM is the engine of the modern SOC, Onum is both the pipeline + filter — streaming high-quality, filtered fuel quickly into the engine to drive more efficient and superior performance. Onum delivers transformational advantages across three critical dimensions: ⚡ Speed: Delivers 5X more events per second than its nearest competitor and processes security and observability data in real-time versus legacy batch and store methods. ⚡ Cost: Smart filtering reduces data storage costs by 50% through intelligent optimization. ⚡ Superior Outcomes: Real-time pipeline detection starts before data enters the Falcon platform, delivering up to 70% faster incident response with 40% less ingestion overhead. The future of cybersecurity is here – built on real-time, high-fidelity data. 👉 Learn more:show more

This Huawei ad I just walked by at Munich... airport hit me like a ton of bricks. Huawei watch? HUAWEI HEALTH? Delivering your intimate, real-time location, behavioral & physiological data (heart rate??) directly to the CCP is absolutely insane. I hadn't even considered how many of these watches must be on people hands right now, and how powerful a tool of espionage (the next-level invasive data gathering!) the CCP has at its disposal. Grok, what countries have the biggest usage per capita of huawei watch? Also, considering what I wrote earlier in this post, and given that Huawei is bound by Chinese law to share all data it has access to with the the Chinese government (and not disclose it is doing so), what impact is there for personal privacy and security for users of Huawei watch?show more

💥❓ Blow up the "Power of Siberia" like the... "Nord Stream"? — Fox News called to destroy the Russian gas pipeline ⚡️On Fox News, there was practically a call for sabotage against Russia: "So, Putin is laying a big old pipeline to China." 🇷🇺🇨🇳 The host emphasized that the project connects Russia and China. "It is supposed to be completed in the next decade and supply 15% of China's energy needs," — the program said. ❗️"Russia and China are getting closer. Someone might have to blow up this pipeline like the 'Nord Stream'," — the host concluded. - Ostashkoshow more