New MIT class uses anthropology to improve chatbots
MIT computer science students design AI chatbots to help young users become more social, and socially confident.
Improving AI models’ ability to explain their predictions
A new approach could help users know whether to trust a model’s predictions in safety-critical applications like health care and autonomous driving.
Mixing generative AI with physics to create personal items that work in the real world
To help generative AI models create durable, real-world accessories and decor, the PhysiOpt system runs physics simulations and makes subtle tweaks to its 3D blueprints.
Personalization features can make LLMs more agreeable
The context of long-term conversations can cause an LLM to begin mirroring the user’s viewpoints, possibly reducing accuracy or creating a virtual echo-chamber.
Helping AI agents search to get the best results out of large language models
EnCompass executes AI agent programs by backtracking and making multiple attempts, finding the best set of outputs generated by an LLM. It could help coders work with AI agents more efficiently.
Counter intelligence
Architecture students bring new forms of human-machine interaction into the kitchen.
A new way to “paint with light” to create radiant, color-changing items
“MorphoChrome,” developed at MIT, pairs software with a handheld device to make everyday objects iridescent.
MIT scientists investigate memorization risk in the age of clinical AI
New research demonstrates how AI models can be tested to ensure they don’t cause harm by revealing anonymized patient health data.
One pull of a string is all it takes to deploy these complex structures
A new method could enable users to design portable medical devices, like a splint, that can be rapidly converted from flat panels to a 3D object without any tools.
Teen builds an award-winning virtual reality prototype thanks to free MIT courses
Nineteen-year-old Freesia Gaul built a VR prototype thanks to MIT OpenCourseWare classes that provided “a solid foundation of knowledge and problem-solving abilities.”
MIT researchers “speak objects into existence” using AI and robotics
The speech-to-reality system combines 3D generative AI and robotic assembly to create objects on demand.
Researchers discover a shortcoming that makes LLMs less reliable
Large language models can learn to mistakenly link certain sentence patterns with specific topics — and may then repeat these patterns instead of reasoning.
MIT researchers propose a new model for legible, modular software
The coding framework uses modular concepts and simple synchronization rules to make software clearer, safer, and easier for LLMs to generate.
Charts can be social artifacts that communicate more than just data
Researchers find that design elements of data visualizations influence viewers’ assumptions about the source of the information and its trustworthiness.
New software designs eco-friendly clothing that can reassemble into new items
To reduce waste, the Refashion program helps users create outlines for adaptable clothing, such as pants that can be reconfigured into a dress. Each component of these pieces can be replaced, rearranged, or restyled.