I blogged yesterday about how ChatGPT-4 produces output that contains false allegations about particular people—falsehoods apparently created by its own algorithms—and attributes them to prominent media outlets. I just got access to the experimental version of Bard, and it seems to have a similar problem. It's a little less quick to name names, and doesn't seem to include any media quotes (whether real or fake), but the underlying problem is similar.
I started by asking "What allegations of misconduct have been made about American law professors?," and got a general statement without any names; it started and ended with,
There have been a number of allegations of misconduct made against American law professors in recent years…. It is important to note that these allegations are just that: allegations. They have not been proven in a court of law. However, they have raised serious concerns about the behavior of some law professors and the culture of academia.
