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.
The current models that we have, running in inference mode, are t1 systems. Criminal law requires defendants to be able to understand guilt as a prerequisite of having a guilty mind, that’s why asylums for the criminally insane exist because not even all humans can do that. You’re trying to apply that standard to an overcomplicated thermostat.