Hmm… That is a good point. Seems like a risky experiment.

The idea with this test setup is based on the idea that the result could potentially provide new information instead of just confirming what I already believe to be true. An inferior experiment would just involve mild flattery, but that can only result in confirmation bias instead of rejecting a hypothesis. Not my favorite type of experiment.

I guess a more passive observational approach is the way to go in this case.