Microsoft researchers have done what many super-nerds only dream about: They got into women’s underwear.
Okay, that’s not quite fair. What they actually did was develop a “smart bra” that senses the mood of whomever wears it to help combat “emotional eating.” And it actually seems to work.
The prototype smart bra contains a number of sensors that can detect a handful of emotions by monitoring heart rate and skin activity (like sweating). The smart bra also packs in a 2-axis gyroscope and a 3-axis accelerometer, which it uses to figure out when someone is scarfing down some sheet cake.
Using machine learning, the smart bra was then able to figure out when the person wearing it was in a mental state that triggered overeating for emotional reasons. According to a paper released by the researchers (PDF), the bra successfully detected rising negative emotions roughly 75 percent of the time. This was backed up by emotional data recorded by the study’s participants in an appropriately named app called EmoTree.
“This is the first study, that we are aware of, that makes use of wearable, mobile sensors for detecting emotions,” the team wrote. “The bra form-factor was ideal because it allowed us to collect EKG [activity] near the heart.”
In the next phase of the experiment, Microsoft’s researchers plan to develop a system that delivers an “appropriately timed, personalized intervention” that will alert the wearer when they are likely to kill a pint of Ben & Jerry’s because they’re upset or stressed out.
Microsoft is not the only company to pack tech into a brassiere. Earlier this year, ad agency OgilvyOne Athens announced the Tweeting Bra, which sends out a tweet every time the undergarment is removed as a way to remind women to check themselves for signs of breast cancer.
Is Microsoft’s smart bra taking wearable tech in the right direction, or bringing it a little too close for comfort?
San Francisco startup Dimensional advertised for people to walk robot dogs through city streets. The New York Times reported that the job could include carrying a roughly 33-pound robot back to the office if it overheated. A lift home is an awkward requirement for a labor-saving machine.
Keeping the hardware running is only one challenge. Anthropic's robotics tests found that language models mostly failed when controlling joints directly, but did better when directing trained controllers. Giving an AI agent a body doesn't teach it to handle ordinary household objects.
Soon, a mattress protector may be more than a bed cover. Australian medtech company Sleeptite and researchers at RMIT University have received a US patent for FlexiSense, a smart bedding technology that tracks body position and posture to help caregivers identify when older residents may be at risk of falling.
The technology is being developed for Sleeptite’s in-bed monitoring system, REMi, and was recently on display at The MedTech Conference in Boston. A peer-reviewed study in Flexible and Printed Electronics says the sensors can also be made at scale without sacrificing performance or durability.
AI companies spend enormous amounts of time convincing us their technology is safe and secure. But what happens when those same companies become targets of increasingly sophisticated AI-powered attacks? Anthropic, the company behind Claude, is now facing that question. According to a Washington Post report, cybersecurity startup Cathedral discovered vulnerabilities that let its researchers access sensitive information in Anthropic's internal systems.
The researchers used AI agents to identify potential entry points in less than 12 hours. Interestingly, they didn't need to crack Claude itself. Instead, they exploited weaknesses in third-party business applications that Anthropic uses for everyday operations. Anthropic's security testing program disclosed the findings, which allows outside researchers to identify and report vulnerabilities.