NewsOfficialXOct 19, 2026, 18:14 UTC

World Foundation Models learn the world from video 🌎

World Foundation Models learn the world from video 🌎 But if the footage only looks forward, the model only understands what’s ahead. Autonomous systems need the full scene. That’s why NATIX builds on real-world multi-camera footage, not just a front view 👀

Open on X ↗

SN72 StreetVision by NATIX at a glance

SN72, StreetVision by NATIX (α token ق), is one of the independent markets on the Bittensor network, each with its own α token and its own price. Its α currently trades at 0.002124 τ (≈ $0.56), against 6,181 τ of pool liquidity. On-chain, the best-delegated validator on it yields about 45.63% APR (simple) and 57.81% APY (compounded), emissions add 0.000000 τ to the pool each block, epochs run every 360 blocks. It was registered at block #5,064,327.

Chart, holders, conviction and every figure →

More from SN72 StreetVision by NATIX

OfficialX · @NATIXNetwork · 3d ago

Models are getting cheaper. Compute is getting easier to buy.

OfficialX · @NATIXNetwork · 4d ago

Physical AI labs are paying for the one thing they can’t generate: real-world data 🌎

OfficialX · @NATIXNetwork · 5d ago

A better model alone won’t get autonomy to scale 🚗

OfficialWebsite · 6d ago

What Happens When Reasoning-Capable Driving Models Go Open Source

OfficialX · @NATIXNetwork · 7d ago

Real data. Real revenue. Real burns 🔥

OfficialX · @NATIXNetwork · 9d ago

World Models simulate reality, but if you feed them nothing but internet data, how much reality are you actually capturing?

OfficialX · @NATIXNetwork · 10d ago

Most World Models today are built on front-facing driving videos. ➡️

OfficialX · @NATIXNetwork · 11d ago

Missed our latest token burn? We've got you covered 😉

Taosis indexes announcements, articles, posts and releases about Bittensor subnets from their own channels and keeps a record of each. The text above is the source’s; the figures are read from the chain by Taosis.