Programming
Programming

Programming

Artificial Intelligence Computer science and technology Lincoln Laboratory Programming Research Security and military studies Software U.S. Armed Forces

How novice coders can develop AI programs for military applications

A USAF cadet and a Lincoln Laboratory researcher found AI chatbots can help nontechnical service members produce viable software applications for their unique problems.

Algorithms Artificial Intelligence Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology Defense Advanced Research Projects Agency (DARPA) Electrical engineering and computer science (EECS) Games machine learning MIT Schwarzman College of Computing MIT Siegel Family Quest for Intelligence MIT-IBM Watson AI Lab National Science Foundation (NSF) Natural language processing Programming Research School of Engineering School of Science

Teaching AI agents to ask better questions by playing “Battleship”

MIT researchers use the classic game as a test bed for AI agents, finding a small AI model can outperform the biggest ones at 1 percent of the cost.

Algorithms Artificial Intelligence Autonomous Underwater Vehicles (AUV) Lincoln Laboratory Programming Robotics Students Woods Hole

Featured video: Coding for underwater robotics

Lincoln Laboratory intern Ivy Mahncke developed and tested algorithms to help human divers and robots navigate underwater.

Algorithms Artificial Intelligence Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology Electrical engineering and computer science (EECS) Human-computer interaction machine learning MIT Schwarzman College of Computing Programming Programming languages Research School of Engineering Software

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.

Artificial Intelligence Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology Electrical engineering and computer science (EECS) Human-computer interaction machine learning MIT Schwarzman College of Computing Programming Programming languages Research School of Engineering Software

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.

Algorithms Artificial Intelligence Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology Electrical engineering and computer science (EECS) Human-computer interaction machine learning MIT Schwarzman College of Computing National Science Foundation (NSF) Programming Programming languages Research School of Engineering Software

Can AI really code? Study maps the roadblocks to autonomous software engineering

A team of researchers has mapped the challenges of AI in software development, and outlined a research agenda to move the field forward.

Artificial Intelligence Arts Design Education, teaching, academics Graduate, postdoctoral Human-computer interaction Maker movement Media Lab MIT Morningside Academy for Design Online learning Profile Programming School of Architecture and Planning Software Students

Combining technology, education, and human connection to improve online learning

Caitlin Morris, a PhD student and 2024 MAD Fellow affiliated with the MIT Media Lab, designs digital learning platforms that make room for the “social magic” that influences curiosity and motivation.

Algorithms Artificial Intelligence Brain and cognitive sciences Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology Electrical engineering and computer science (EECS) machine learning MIT Schwarzman College of Computing Programming Programming languages Research School of Engineering School of Science

Making AI-generated code more accurate in any language

A new technique automatically guides an LLM toward outputs that adhere to the rules of whatever programming language or other format is being used.

Artificial Intelligence Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology Data Defense Advanced Research Projects Agency (DARPA) Department of Energy (DoE) Electrical engineering and computer science (EECS) machine learning MIT Schwarzman College of Computing National Science Foundation (NSF) Programming Research

User-friendly system can help developers build more efficient simulations and AI models

By automatically generating code that leverages two types of data redundancy, the system saves bandwidth, memory, and computation.

Algorithms Artificial Intelligence Arts Classes and programs Collaboration Computer science and technology Digital humanities Electrical engineering and computer science (EECS) Graduate, postdoctoral Human-computer interaction machine learning Media Lab MIT Schwarzman College of Computing Music Music and theater arts Music technology Programming School of Engineering School of Humanities Arts and Social Sciences Software Technology and society

MIT launches new Music Technology and Computation Graduate Program

The program will invite students to investigate new vistas at the intersection of music, computing, and technology.