✳flâneur — a map of the web's best reading

how we accidentally solved robotics by watching 1 million hours of YouTube | atharva's blog

ksagar.bearblog.dev · 1,276 words · saved by 5 readers

imagine this: you've just spent $640 billion training the chonkiest language model known to humanity (lol) and decide to call it "Behemoth". it can annoy you on whatsapp, try to solve calculus, and argue with you about anything with a sophistication of a philosophy PhD. but ask it to grab a coffee mug from your kitchen counter? ngmi turns out scaling LLMs forever still leaves robots as clueless. internet-scale language misses the fundamental physics of stuff actually moving around in 3D space. and no amount of "think step by step" or COT prompting helps to teach your chatterbox where the trash is in the kitchen but if i told you that the solution was hiding in plain sight? what if the secret sauce wasn't more tokens, but more... videos? here's the thing everyone forgot while we were busy making ai agents book flight tickets: robots need to understand physics, not language. so enter V-JEPA 2, which basically said "hey, what if we fed a neural network 1 million hours of youtube and taugh

how we accidentally solved robotics by watching 1 million hours of YouTube – atharva's blog how we accidentally solved robotics by watching 1 million hours of YouTube 29 Jun, 2025 the existential crisis we all share imagine this: you've just spent $640 billion training the chonkiest language model known to humanity (lol) and decide to call it "Behemoth". it can annoy you on whatsapp, try to solve calculus, and argue with you about anything with a sophistication of a philosophy PhD. but ask it to grab a coffee mug from your kitchen counter? ngmi turns out scaling LLMs forever still leaves robot

Explore this link on the map →

saved by

related reading