A new way to let AI chatbots converse all day without crashing
Researchers developed a simple yet effective solution for a puzzling problem that can worsen the performance of large language models such as ChatGPT.
Human-computer interaction
Reasoning and reliability in AI
PhD students interning with the MIT-IBM Watson AI Lab look to improve natural language usage.
Leveraging language to understand machines
Master's students Irene Terpstra ’23 and Rujul Gandhi ’22 use language to design new integrated circuits and make it understandable to robots.
Automated system teaches users when to collaborate with an AI assistant
MIT researchers develop a customized onboarding process that helps a human learn when a model’s advice is trustworthy.
New method uses crowdsourced feedback to help train robots
Human Guided Exploration (HuGE) enables AI agents to learn quickly with some help from humans, even if the humans make mistakes.
Explained: Generative AI
How do powerful generative AI systems like ChatGPT work, and what makes them different from other types of artificial intelligence?
To excel at engineering design, generative AI must learn to innovate, study finds
AI models that prioritize similarity falter when asked to design something completely new.
A method to interpret AI might not be so interpretable after all
Some researchers see formal specifications as a way for autonomous systems to "explain themselves" to humans. But a new study finds that we aren't understanding.
AI copilot enhances human precision for safer aviation
Designed to ensure safer skies, “Air-Guardian” blends human intuition with machine precision, creating a more symbiotic relationship between pilot and aircraft.
Is AI in the eye of the beholder?
Study shows users can be primed to believe certain things about an AI chatbot’s motives, which influences their interactions with the chatbot.