We've all been astonished at how chatbots seem to understand the world. But what if they were truly connect to the real world? What if the dataset behind the chat interface was physical reality itself, captured in real time by interpreting the input of billions of sensors sprinkled around the globe? As cofounder and CEO Ivan Poupyrev puts it, "Think of ChatGPT, but for physical reality." Archetype's foundational model is called Newton.

Nearly two decades after its release, "Minority Report" still seems to be as prescient as the film's eerie crime-fighting "precogs," offering a clarifying vision of the future that continues to manifest in the real world. Though it debuted way back in 2002, the film highlighted technologies like driverless cars, hyper-targeted advertising and robotic insects -- all of which exist in 2019. Now, it appears Steven Spielberg's cinematic premonition may have included another technology that is potentially one step closer to reality: gesture-controlled sensing technology. Translated to English: technology that would allow us to control televisions, smartphones and computers without touching them, not unlike Tom Cruise's character, John Anderton, manipulating floating digital images like a conductor directing an orchestra (though he uses gloves instead of a baton). For years, Google's Advanced Technology and Projects (ATAP) lab has been seeking to create motion sensors that might be used in similar technology, an effort the company dubbed Project Soli.

"We've developed a vision where the hand is the only controller you need," said Ivan Poupyrev, a technical program lead at Google's Advanced Technology and Projects (ATAP) group. Basically, Google is trying to create a whole new gesture language for every device in your home. After rolling out a Project Soli alpha developer kit last year, Google selected 60 developers from a pool of 180 applicants to show off how their implementations. One group used Soli to used it to identify materials like copper, while another used it for 3D imaging. The coolest experiment, though, was using it as an in-car remote control. Imagine using gesture controls in your car by just having to raise your fingers from the steering wheel a bit.