Intel debuted the reference design for its 'Jarvis' smart headset back at CES, promising that it would eventually come to serve the same voice-recognition functions that we would expect from the likes of Siri and Google Now. Beyond Intel's promises, however, it didn't seem to have many differentiating attributes. Quartz now reports that the Jarvis' voice capabilities won't rely on the cloud, making the experience faster and hopefully more useful.

Intel's New Devices Group head Mike Bell spoke with Quartz about making Jarvis more powerful than its competitors, using technology that mobile devices like wearables have up until now had no access to. Bell explains that devices that rely on the cloud are captive to sometimes unreliable connectivity. "How annoying is it when you’re in Yosemite and your personal assistant doesn’t work because you can’t get a wireless connection?" Instead of depending on distant servers, new processors like the company's Edison prototype would do all the heavy lifting.

Bell's vision is lofty, of course, especially since Jarvis is nowhere near market-ready. But Intel at least appears committed to standing at the forefront of the ever emergent wearables space.