@michael-lepori.bsky.social, Ellie Pavlick and @thomasserre.bsky.social have found that LLMs can develop a mathematical “understanding” that differentiates between events ranging from commonplace to impossible.
www.brown.edu/news/2026-04-22/artificial-intelligence-understanding-real-world
New research shows that AI language models can develop a mathematical “understanding” that differentiates between events that are commonplace, improbable, impossible or just plain nonsense.
