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.
Lincoln Lab unveils the most powerful AI supercomputer at any US university
Optimized for generative AI, TX-GAIN is driving innovation in biodefense, materials discovery, cybersecurity, and other areas of research and development.
System lets people personalize online social spaces while staying connected with others
By enabling users to easily create social apps that serve communities’ needs, the Graffiti framework aims to promote healthier online interactions.
MIT software tool turns everyday objects into animated, eye-catching displays
The FabObscura system helps users design and print barrier-grid animations without electronics, and can help produce dynamic household, workplace, and artistic objects.