原推：That the AI language model breakthrough applies to so many domains
(autonomous taxis, long read gene sequence reconstruction, here robotic capability)
makes me suspect that the image generation breakthrough (diffusion) will have similar cross-domain applicability https://t.co/CuI7aKmZmi
Introducing RT-1, a robotic model that can execute over 700 instructions in the real world at 97% success rate!
Generalizes to new tasks✅
Robust to new environments and objects✅
Fast inference for real time control✅
Can absorb multi-robot data✅
Powers SayCan✅
?? https://t.co/HNcRZAPIl0