Skip to main content

‘Airwriting’ glove lets you text by writing in the air

airwriter
Image used with permission by copyright holder

The increasing number of gesture-control technologies being introduced these days means that a time may actually come when you can control your whole house with just the wave of a hand. Hot on the heels of the MYO armband that lets you control Macs and PCs through gesture is the “Airwriting” glove – a glove that gives you the power to compose emails and text messages by writing on, you guessed it, air. 

The glove, developed by researchers from the Karlsruher Institut für Technologie in Germany, contains sensors that record hand movements. A computer system captures and decodes those movements. It has the capacity to differentiate between gestures meant to spell words and random, unrelated gestures, so you can wear the glove just fine and airwrite whenever you like while doing something else. “All movements that are not similar to writing, such as cooking, doing laundry, waving to someone, are ignored,” Doctorate student Christoph Amma, one of the developers, said on airwriter’s press release. “The system runs in the background without interpreting every movement as computer input.”Amma believes that the technology could eventually be incorporated into clothing – like a wristband – for everyday use.

The system currently recognizes capitalized letters and has a total vocabulary of 8,000 words. But, since the glove is just a prototype, it’s nowhere near perfect. It has an 11 percent error rate that goes down to 3 percent the more you use it and the more the system gets used your movements. Amma and fellow developer Professor Tanja Schultz recently received the Google Faculty Research Award worth $81,000, meant to be used to develop the technology for mobile devices, which means that in the future, America’s fastest texter could also be the the nation’s best charades player. 

Mariella Moon
Former Digital Trends Contributor
Mariella loves working on both helpful and awe-inspiring science and technology stories. When she's not at her desk writing…
A dangerous new jailbreak for AI chatbots was just discovered
the side of a Microsoft building

Microsoft has released more details about a troubling new generative AI jailbreak technique it has discovered, called "Skeleton Key." Using this prompt injection method, malicious users can effectively bypass a chatbot's safety guardrails, the security features that keeps ChatGPT from going full Taye.

Skeleton Key is an example of a prompt injection or prompt engineering attack. It's a multi-turn strategy designed to essentially convince an AI model to ignore its ingrained safety guardrails, "[causing] the system to violate its operators’ policies, make decisions unduly influenced by a user, or execute malicious instructions," Mark Russinovich, CTO of Microsoft Azure, wrote in the announcement.

Read more