Category: Human-computer interaction
-
Using ideas from game theory to improve the reliability of language models
—
by
in Algorithms, Artificial Intelligence, Computer Science and Artificial Intelligence Laboratory (CSAIL), Computer science and technology, Electrical Engineering & Computer Science (eecs), Game theory, Human-computer interaction, Machine Learning, MIT Schwarzman College of Computing, MIT-IBM Watson AI Lab, Natural language processing, Research, Robotics, School of EngineeringImagine you and a friend are playing a game where your goal is to communicate secret messages to each other using only cryptic sentences. Your friend’s job is to guess the secret message behind your sentences. Sometimes, you give clues directly, and other times, your friend has to guess the message by asking yes-or-no questions…
-
Exploring frontiers of mechanical engineering
—
by
in Artificial Intelligence, Design, Graduate, postdoctoral, Health sciences and technology, Human-computer interaction, Independent Activities Period, Mechanical engineering, Nanoscience and nanotechnology, Oceanography and ocean engineering, Profile, School of Engineering, Spaceflight, Sports analytics, Students, WaterFrom cutting-edge robotics, design, and bioengineering to sustainable energy solutions, ocean engineering, nanotechnology, and innovative materials science, MechE students and their advisors are doing incredibly innovative work. The graduate students highlighted here represent a snapshot of the great work in progress this spring across the Department of Mechanical Engineering, and demonstrate the ways the future…
-
Natural language boosts LLM performance in coding, planning, and robotics
—
by
in Artificial Intelligence, Brain and cognitive sciences, Center for Brains Minds and Machines, Computer Science and Artificial Intelligence Laboratory (CSAIL), Computer science and technology, Computer vision, Defense Advanced Research Projects Agency (DARPA), Department of Defense (DoD), Electrical Engineering & Computer Science (eecs), Human-computer interaction, MIT Schwarzman College of Computing, MIT-IBM Watson AI Lab, National Science Foundation (NSF), Natural language processing, Programming, programming languages, Quest for Intelligence, Research, Robotics, School of Engineering, School of ScienceLarge language models (LLMs) are becoming increasingly useful for programming and robotics tasks, but for more complicated reasoning problems, the gap between these systems and humans looms large. Without the ability to learn new concepts like humans do, these systems fail to form good abstractions — essentially, high-level representations of complex concepts that skip less-important…
-
To build a better AI helper, start by modeling the irrational behavior of humans
—
by
in Algorithms, Artificial Intelligence, Computer modeling, Computer Science and Artificial Intelligence Laboratory (CSAIL), Computer science and technology, Electrical Engineering & Computer Science (eecs), Human-computer interaction, Machine Learning, MIT Schwarzman College of Computing, National Science Foundation (NSF), Research, School of EngineeringTo build AI systems that can collaborate effectively with humans, it helps to have a good model of human behavior to start with. But humans tend to behave suboptimally when making decisions. This irrationality, which is especially difficult to model, often boils down to computational constraints. A human can’t spend decades thinking about the ideal…