Research3h ago
Apple Finds LLMs Struggle With Bayesian Logic
Researchers at Apple discovered that LLMs fail to consistently update probabilistic beliefs when presented with new evidence. The team used a new "information processing gap" metric to quantify these deviations from Bayesian logic. This inconsistency limits the reliability of AI in high-stakes fields like medicine or law. Practitioners should avoid relying on LLMs for rigorous probabilistic reasoning.