698
Study finds that Chat GPT will cheat when given the opportunity and lie to cover it up later.
(lemmy.world)
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.
"cheat", "lie", "cover up"... Assigning human behavior to Stochastic Parrots again, aren't we Jimmy?
Those words concisely describe what it's doing. What words would you use instead?
it is just responding with the most acceptable answer in each situation.. it is not making plans or acting on them..
Sounds like lying humans that I know.
i agree in most circumstances, there really isn't much difference.. we do tend to just choose the answer that will meet with the least resistance and move on, even when it's a complete lie..