November 7, 2024 | Benjamin Daniel
Despite its impressive output, generative AI doesn’t have a coherent understanding of the world
New research co-authored by MIT economist Ashesh Rambachan shows that even the best-performing large language models don’t form a true model of the world and its rules, and can thus fail unexpectedly on similar tasks.
Share a Story
Do you have a story to share about an event, a publication, or someone in the community who deserves a spotlight? Reach out to the SHASS Communications Team with your idea.
View All in the Media