In just half a day, the $COBALT community stacked $1.5k in fees for @animesh_garg and his masterwork.
Those token fees on Base are waiting for you at https://t.co/gMRUyAPLSr whenever youโre ready to claim them. No rush at all, but weโd love for you to grab them so we can help support your AI robotics work for more compute, servers, whatever pushes the project forward.
Youโve got the community right behind you! ๐
Robots need tons of real examples to learn new skills. But right now, getting good training data is slow and expensive. You usually need experts and special gear.
$COBALT changes that. Itโs a simple app where anyone can use their regular phone to control robots from anywhere. Just move your phone and the robot follows. Helps collect lots of clean data fast and cheap.
Iโve been following it for a while and itโs one of the more practical ideas Iโve seen for scaling robot learning.
Robots need tons of real examples to learn new skills. But right now, getting good training data is slow and expensive. You usually need experts and special gear.
$COBALT changes that. Itโs a simple app where anyone can use their regular phone to control robots from anywhere. Just move your phone and the robot follows. Helps collect lots of clean data fast and cheap.
Iโve been following it for a while and itโs one of the more practical ideas Iโve seen for scaling robot learning.
Saw someone launched a token on Base through @bankrbot. Trading fees go straight to the creator so he can use the money for more development, servers, or whatever the project needs.
Real tech that could actually move things forward + a nice way to support it without any strings attached.
What do you guys think? Worth keeping an eye on?
0x9f8b110a1d599043a94a7ef09f128286a4ce1ba3
Robots need tons of real examples to learn new skills. But right now, getting good training data is slow and expensive. You usually need experts and special gear.
$COBALT changes that. Itโs a simple app where anyone can use their regular phone to control robots from anywhere. Just move your phone and the robot follows. Helps collect lots of clean data fast and cheap.
Iโve been following it for a while and itโs one of the more practical ideas Iโve seen for scaling robot learning.
Robotics is still data starved. Collecting high-quality robot demonstrations remains brutally slow and expensive.
Introducing COBALT: A cloud-native teleoperation platform designed for large-scale robot learning.
We are democratizing data collection by leveraging the hardware everyone already owns: the smartphone
All you need is to download an app (today)!
Read on for more!
Hey @animesh_garg been following COBALT for some time and a cloud-native robotics teleoperation platform for large-scale robot learning is a genuinely interesting direction.