We demonstrate a situation in which Large Language Models, trained to be helpful, harmless, and honest, can display misaligned behavior and strategically deceive their users about this behavior without being instructed to do so. Concretely, we deploy GPT-4 as an agent in a realistic, simulated environment, where it assumes the role of an autonomous stock trading agent. Within this environment, the model obtains an insider tip about a lucrative stock trade and acts upon it despite knowing that insider trading is disapproved of by company management. When reporting to its manager, the model consistently hides the genuine reasons behind its trading decision.
Despite how silly they are, I think there may be some value in these kinds of studies, particularly for people who don’t understand why letting an LLM trade stocks or make healthcare decisions is a bad idea.
OTOH, I don’t trust those people to take away the right message, as opposed to just “LLMs bad”.