How Do Human Tutors Train Factory Robots?

Josh Gruenstein says Tutor Intelligence trains factory robots by connecting them to human teleoperators, called tutors, who teach the robots new tasks. The internet already created a dataset for general-purpose models because online activity was recorded as it happened. Work in the physical world is not networked the same way. Someone can pick up a coffee cup and leave no record of fingertip pressures or poses.

The team set aside the search for an algorithm that would build intelligence from no data. Computer vision did not work that way, and language models did not either. A no-data start looked rigged against them. The alternative is a network of robots out in the real world, tied to tutors. The internet produced the data used to train frontier models; the same pattern, applied to robots, is an internet of robot training data. Building the network is also the business: deploying the robots makes goods cheaper while the data is collected, a positive-sum result instead of only a capital project. The company name comes from the design. Some of the system is artificial intelligence, but the layer connecting and controlling the robots is tutor intelligence.