“Computer scientists from Stanford University and Carnegie Mellon University have evaluated 11 current machine learning models and found that all of them tend to tell people what they want to hear…”

  • manuallybreathing@lemmy.ml
    link
    fedilink
    English
    arrow-up
    25
    ·
    11 days ago

    But as the paper points out, one reason that the behavior persists is that “developers lack incentives to curb sycophancy since it encourages adoption and engagement.”

    you’re absolutely right!