No Widgets found in the Sidebar

Check out this mind-blowing demo of Figure 01, a robot that can see, talk, and even grab stuff!

How it Works

Figure 01 uses a fancy new technology called a Visual Language Model (VLM) to understand the world around it. This VLM is like a super-smart brain that can process images and language at the same time.

The Demo

In the demo, Figure 01 shows off its skills by:

  • Identifying objects like an apple and a dish rack
  • Grabbing the apple when asked for something to eat
  • Explaining why it gave the apple and cleaning up trash while talking

The Brains Behind Figure 01

Figure 01 is the result of a collaboration between OpenAI and Figure, a startup led by some of the brightest minds from companies like Boston Dynamics and Tesla.

Not Just a Toy

Unlike Elon Musk’s Optimus robot, Figure 01 is not controlled remotely. It can operate independently, making it a potential game-changer for industries like manufacturing and healthcare.

The Future of Robots

The founder of Figure, Brett Adcock, believes that Figure 01 is just the beginning. He envisions a future where super-advanced AI systems control billions of humanoid robots, transforming our world in ways we can’t even imagine.