Researchers have created a noninvasive (无创的) brain decoder that can translate stories heard by participants into a string of text, based on their MRI scans. The team says this technology could one day aid communication in people who are mentally conscious but physically unable to speak, such as stroke patients.

“Compared to what’s been done before using the same noninvasive method, which typically deals with single words or short sentences, this new technology is a real leap forward,” Alex Huth, a professor of neuroscience and computer science at the University of Texas at Austin, says in a statement. “We’re getting the model to decode continuous language for extended periods of time with complicated ideas.”

Huth and his colleagues collected hours of data from three participants listening to the podcasts “Modern Love” and “The Moth Radio Hour” while connected to a functional MRI (fMRI) scanner, which recorded the participants’ blood oxygen levels in parts of their brains. This data was used to train an A. I. model to match specific brain activity patterns with strings of words, the team reports in a new study published Monday in Nature Neuroscience. The decoder used GPT-1, an earlier version of the technology that powers ChatGPT.

When the participants listened to new stories, the tool couldn’t spit back the exact words, but it could convey the main idea. For example, a participant hearing “I don’t have my driver’s license yet” had their thoughts translated to: “She has not even started to learn to drive yet.” The researchers also had participants watch muted animated short films. Though the model was trained only on spoken words, it could still generate a language description of what was happening.

Reading minds raises a multitude of ethical questions about brain privacy, but the researchers say their tool doesn’t work without willing cooperation. “This is all about the user having a new way of communicating, a new tool that is totally in their control,” David Moses, a researcher of automatic speech recognition at the University of California, San Francisco, who was not involved in the study, said. “That is the goal, and we have to make sure that stays the goal.”

Here’re some of the excellent inventions in 2023. Which one do you like most?

The paint on a white building reflects 80 to 90% of the sunlight that strikes it. The rest of the light warms the surrounding area, raising air-conditioning bills. But the Whiter Paint is made of chemicals that better reflect UV rays. It reflects up to 98% of the sunlight, which could reduce AC use by 40%. “The heat is reflected into deep space,” says Xiulin Ruan, who led the Purdue University team that created the paint.

Now you can take music lessons on a smartphone, using this app, which uses an on-screen piano to teach basics such as harmony and beat. You learn by interacting with more than 200 popular pieces of music. Just match sounds to notes and play along. “You don’t need natural talent to learn music,” says Karen Chow, who’s a learning scientist at Duolingo.

Model A, developed by Alef Aeronautics, is a two-seat all-electric vehicle with a flight range of 110 miles. And it looks as if it were made to be parked in a garage. In July, 2023, the Federal Aviation Administration gave Ale f permission to take the vehicle on test flights. The company hopes to deliver the first Model A by 2026.

They’re actually battery-powered shoes with wheels. They let you walk normally—just faster and more easily. Moonwalkers, made by Shift Robotics, use AI to sense when you’re speeding up or slowing down, and adjust themselves accordingly. With it, you can walk at speeds up to seven miles per hour.

Every year, TIME selects the best inventions that are making the world better, smarter and — in some cases—a little more fun. Here’s which ones made this year’s unranked list.

●Morpher

People refuse to wear a helmet because they’re thick and bulky. Morpher, a bike helmet made from interweaved plastics that is just as strong as its traditional helmets, but flexible enough to fold almost totally flat, making it easier to transport. Morpher has raised almost $300,000 on Indiegogo and may be available for sale in stores in future.

● Hyper Adapt

Almost everyone who sees the movie Back to the Future wants a pair of self-lacing shoes. Now, thanks to Nike, the shoe dream is a reality. When wearers press a button near the tongue, the Hyper Adapt 1.0s automatically tighten and loosen around their foot. Simplified shoe fastening could give users an edge during sports competition, and it’s especially useful for people with impaired（受损的） motor function.

●Hello Sense

It's hard to believe that an alarm clock could not only be beautiful but also improve your sleep. That it could monitor the temperature, humidity(湿度), light and even air quality in your bedroom to help you engineer a perfect sleep environment. That it could monitor your sleep cycles and wake you when you’re least likely to feel groggy—all thanks to simple voice commands.

●Eatwell Assistive Tableware

It is hard for Alzheimer’s patients to use silverware without spilling. Eatwell Assistive Tableware is a dining set designed to make mealtime easier for people with Alzheimer’s and other diseases that affect brain and body function. The tableware uses bright colors to help people distinguish their plates from their food and putting wide rubber bases on the cups to prevent spills.