Generalist's GEN-1.5 pushes robots toward learning tasks from a short demonstration
AIGeneralist is building robot foundation models trained on large-scale physical data, so new tasks may need only a short demonstration rather than a dedicated dataset. Across GEN-0, GEN-1, and GEN-1.5, the company reports roughly 99% success on selected tasks and moves toward in-context physical prompting.
Source details
The Sequence · Jesus Rodriguez · thesequence.substack.comPublished · added here
Original title: The Sequence Robotics - Issue #957: Generalist and the Rise of Promptable Robots