To build a better AI helper, start by modeling the irrational behavior of humans
A new technique can be used to predict the actions of human or AI agents who behave suboptimally while working toward unknown goals.
A new technique can be used to predict the actions of human or AI agents who behave suboptimally while working toward unknown goals.
Researchers create a curious machine-learning model that finds a wider variety of prompts for training a chatbot to avoid hateful or harmful output.
With help from a large language model, MIT engineers enabled robots to self-correct after missteps and carry on with their chores.
Researchers demonstrate a technique that can be used to probe a model to see what it knows about new subjects.
After acquiring data science and AI skills from MIT, Jospin Hassan shared them with his community in the Dzaleka Refugee Camp in Malawi and built pathways for talented learners.
Researchers developed a simple yet effective solution for a puzzling problem that can worsen the performance of large language models such as ChatGPT.
PhD students interning with the MIT-IBM Watson AI Lab look to improve natural language usage.
Master’s students Irene Terpstra ’23 and Rujul Gandhi ’22 use language to design new integrated circuits and make it understandable to robots.
MIT researchers develop a customized onboarding process that helps a human learn when a model’s advice is trustworthy.
Human Guided Exploration (HuGE) enables AI agents to learn quickly with some help from humans, even if the humans make mistakes.