5.
AURA: 4 KB of robot memory that knows when not to write
AURA keeps VLA memory constant at 4,224 bytes and cuts robot memory writes by up to 9x without hurting closed-loop success
@josefchen on Backlist
2 appearances on the backlist front page in the last 30 days.
9.
Physical AI is runtime-poor, not compute-poor
A robot serves one token stream at a time, so cheap edge GPUs can beat high-end datacenter GPUs on cost per useful token despite far lower bandwidth