Programming

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.

Read More

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.

Read More

LLMs develop their own understanding of reality as their language abilities improve

In controlled experiments, MIT CSAIL researchers discover simulations of reality developing deep within LLMs, indicating an understanding of language beyond simple mimicry.

Read More