Breakthroughs, discoveries, and DIY tips sent every weekday. A first-of-its-kind, soft, vest-like wearable designed by Harvard researchers could help stroke survivors and people living with ALS regain crucial upper limb movement. The researchers call the device a "wearable robot," which uses inflatable balloons positioned under a patient's arm that bulge and contract based on the desired movement. A combination of machine learning software and a separate physics-based model helps the robot interpret the patient's intended movements and personalize actions accordingly. In testing, the robot was able to correctly identify the user's intended shoulder movement 94.2 percent of the time.

Large language models such as GPT, Llama, Claude, and DeepSeek can be so fluent that people feel it as a "you," and it answers encouragingly as an "I." The models can write poetry in nearly any given form, read a set of political speeches and promptly sift out and share all the jokes, draw a chart, code a website. How do they do these and so many other things that were just recently the sole realm of humans? Practitioners are left explaining jaw-dropping conversational rabbit-from-a-hat extractions with arm-waving that the models are just predicting one word at a time from an unthinkably large training set scraped from every recorded written or spoken human utterance that can be found--fair enough--or a with a small shrug and a cryptic utterance of "fine-tuning" or "transformers!" These aren't very satisfying answers for how these models can converse so intelligently, and how they sometimes err so weirdly.

A new AI system that predicts the health spans of mice could help develop life-extension interventions for humans, according to the tool's inventors. The system analyzes established measures of frailty to gauge a mouse's chronological age and their so-called biological age -- the condition of their physical and mental functions. It was created by researchers from Harvard Medical School's Sinclair Lab, who say it's the first study to track a mouse's frailty for the duration of its life. They plan to use the predictions to quickly test interventions intended to extend the mice's lives and move towards doing the same in humans. "It can take up to three years to complete a longevity study in mice to see if a particular drug or diet slows the aging process," said study co-first author Alice Kane, a research fellow in genetics at Harvard Medical School's Sinclair Lab.

When Facebook chief executive Mark Zuckerberg testified in front of the US Congress, technology experts quickly realized how poorly informed his questioners were. As much as Congress wanted to regulate the tech behemoth, it was clear they had no idea how. Instead, they let him get away with grandiose claims about how AI would solve all the company's problems. For Dipayan Ghosh, a research fellow at the Harvard Kennedy School (HKS), the hearing emphasized the pressing need to bring US policymakers up to speed on major technology issues--and AI in particular. "AI is a tremendous technology, but there are really salient problems that we've seen take a life of their own in society," says Ghosh, who was a technology policy advisor in the Obama administration.

Researchers have created a robot that can slither like a snake - and it might be used in laparoscopic surgeries. The invention is the latest in a slew of new robotic developments. Engineers have recently come up with robots that can glide across water, open doors and lift up to 1,000 times their weight. Now, scientists from Harvard have created one that can slither using artificial scales, according to new research published in Science Robotics. Researchers designed the'robot snake' by using a type of paper cutting art, called kirigami, to engineer the device.

Love them or hate them, computers are becoming more ingrained in 21st century medical care. And in an increasingly data-driven industry, medical education hasn't kept pace. Physicians might curse their computers for sucking time away from patients or turning them into "data entry clerks," but computers aren't to blame, according to two health policy researchers from Harvard Medical School. As algorithms gradually outperform the human mind, clinicians need to place more emphasis on data science to get the most out of advanced analytics and machine learning that could have a significant impact on medical care care. "Today's medical education system is ill-prepared to meet these needs," Ziad Obermeyer, M.D., and Thomas H. Lee, M.D., who also serves as chief medical officer at Press Ganey, wrote in the New England Journal of Medicine.

The stingray-bot is made up of four distinct layers: a silicone substrate that forms its body, a skeletal system made of gold wire, a second layer of silicone that insulates the skeleton and, finally, 200,000 genetically-engineered rat cells. Those cells are designed to contract when exposed to a specific wavelength of light. When they do, the robot effectively swims in the same undulating manner as its namesake. What's more, the "biological life-form," as lead researcher, Kit Parker, describes it, automatically follows the light source as it swims through the nutrient-rich liquid that keeps its cells alive, allowing it to be remotely controlled. The bio-bot can't survive outside of the lab yet.

Harvard researchers have been working on their robot bee for a really, really long time (in robot years). It's impressively small, being bee-sized, but it turns out that it's so small that it's not realistic to expect it to fly with onboard power and computing in the near future. Plus, the flight dynamics of tiny insects like bees is significantly different from larger insects like butterflies and moths, which exhibit combinations of flapping, gliding, and soaring flight. To explore this, Harvard researchers have developed FWMAV, a novel insect-scale flapping-wing micro-air vehicle that's just small enough to be called "micro" and just big enough to operate completely untethered.