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.

https://arxiv.org/abs/2311.07590

  • Bilb!@lem.monster
    link
    fedilink
    English
    arrow-up
    8
    ·
    11 months ago

    Stochastic Parrot

    For what it’s worth: https://en.wikipedia.org/wiki/Stochastic_parrot

    The term was first used in the paper “On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜” by Bender, Timnit Gebru, Angelina McMillan-Major, and Margaret Mitchell (using the pseudonym “Shmargaret Shmitchell”). The paper covered the risks of very large language models, regarding their environmental and financial costs, inscrutability leading to unknown dangerous biases, the inability of the models to understand the concepts underlying what they learn, and the potential for using them to deceive people. The paper and subsequent events resulted in Gebru and Mitchell losing their jobs at Google, and a subsequent protest by Google employees.