We have 2M hours of egocentric human experience recorded. While it's the largest library of datasets, it is also the least informative number we publish. Two recordings of equal duration can differ by an order of magnitude in what a model can learn from them. One holds repetitive tabletop pick-and-place under fixed conditions. The other holds bimanual manipulation across changing states, with precise geometry, varied contacts, coordinated fingers and tool use. Equal duration, nowhere near equal learning value. Effective experience ≈ hours × information per hour. At ten thousand hours that difference is noise. At ten million it is the difference between a corpus and an archive.

Left hand holds the jar, right hand unscrews the lid. A label that just says "open container" loses that, and a robot with two arms needs it. MaxVLM, our in-house video model, labels what each hand does and when each action starts. It got 13 of the 14 actions in this clip right.

A fresh look for what's next. Maxinsights, reimagined. Rooted in human experience. Built for what's next.

MaxGlove records what a camera can't see: how hard a hand grips, how heavy an object is, and how contact shifts through a task.

glad they left the stuck pucks in. how does it figure out one's misplaced in the first place?

Say hello to our new logo. The US office celebrated Friday with fruit cake and boba. Sample size: one cake. We're calling it statistically significant.

Four levels of language annotation on one clip: Environment: Cafe Task: Prepare a latte with latte art Subtask: Pick up the coffee sifter Instruction: Right hand picks up the coffee sifter Plus 3D hand pose (<4 mm), body joints (<2 cm) and hand contact heatmaps.

we'd put the data pipeline right up there with the gpus as a bottleneck. feed it clean egocentric data and you need a lot less compute to get to a policy you can actually use

Our own models now label 90% of our egocentric data. At the start of 2025 they labelled none of it, and people did every hour by hand. Our quality score was 8.5 back then, 8.6 in late 2025 when we were at 40% automatic, and it's 8.9 now. MaxEgo does the hands and body labels and MaxVLM does video, and both are trained on our own data. People still check what they produce, and 98% of what we ship also goes through a four stage automated QA system. For 2026 Q4 we're aiming for 99% automatic at 9.2, and we haven't measured that one yet.

Physical AI learns from people. So did our logo. Meet the new Maxinsights mark: { ] It's open on purpose, a space for what matters. So we handed our team a marker and let them fill it in. The story behind the mark comes later this week. What goes in yours?

Four orders of magnitude of human egocentric video, and the only pseudo-actions Dyna-2 got were 3D hand tracks. It kept improving the whole way. The ablation's the bit we've reread more times than we'd like to admit. Train on actions only and cross-embodiment scaling doesn't show up the same way. Throw in video prediction plus co-training on more human video and it shows up. Next order of magnitude, how good do the hand tracks actually need to be? maxinsights.ai/blog/Beyond_1…

This is the input. One head-mounted camera, one person, one ordinary task. Hand joints, the object, and where the hand is making contact, all from that single view. Our CTO shows you what comes out of it on Monday.

Maxinsights is heading to #IROS2026! Meet our team at Booth 630 to talk real-world data for robotics and explore ways to collaborate. Real-world data. Real conversations. See you there!