What started as an 8-hour demo became something nobody in the humanoid robotics industry had ever done before. On the morning of May 13, 2026, Figure AI started a livestream with a simple plan: deploy three Figure 03 humanoid robots in a warehouse-style package sorting environment, run them for eight hours, demonstrate autonomous operation, and close the stream. Then the robots just... kept going.

After the first 24 hours, there had been zero failures. Brett Adcock, Figure AI's founder and CEO, posted on X: "Our original goal was an 8-hour run. After zero failures yesterday, we decided to keep going. We're now over 24 hours of continuous autonomous operation without a failure." By Day 9, the stream had clocked 191+ consecutive hours of fully autonomous operation running Helix-02, with the robots sorting a total of 238,000 packages.

What the robots were actually doing

Figure AI placed three F.03 humanoid robots in a logistics sorting scene and streamed continuously. Viewers nicknamed the robots Bob, Frank, and Gary. Beside a conveyor belt, they identified packages, picked them up, rotated them, scanned barcodes, and placed them back on the belt. Simple on paper, genuinely hard for a robot.

The task requires solving several real-time perception problems simultaneously:

  • Recognizing packages of different shapes, materials, and sizes
  • Estimating grasp points and adjusting for weight variance
  • Avoiding deforming soft parcels or knocking boxes off the belt
  • Maintaining rhythm without slowing the conveyor
  • Recovering from failures instead of freezing

Humans average around 3 seconds per package. F.03 is now around human parity. "The robots are reasoning directly from camera pixels," Adcock said. That last point is the key technical claim: this is not a scripted motion replay, it is live inference.

Helix-02: the brain behind the arms

Alpha Signal

Don't miss what's next in AI

Join 300,000+ engineers and researchers who get the signal, not the noise.

  • Full access to in-depth AI research breakdowns
  • Be the first to know what's trending before it hits mainstream
  • Daily curated papers, repos, and industry moves