This is the source code for the research around the Noise Audit of Large Language Models (LLMs) GPT-3.5-turbo and GPT-4, in comparison to a Noise audit of 52 students of EMBA program.
vybe / llm-noise-study Goto Github PK
View Code? Open in Web Editor NEWA study that measures and compares LLM decision-making Noise to humans
License: MIT License