I would call it obedience, and it's not the same as friendliness.

The difference, in a repeated prisoner dilemma: Friendliness is cooperating on the first move, and then conditionally. Obedience is always cooperating.

My point is that LLMs are not humans, so projecting intuitions from human psychology onto LLMs is not helpful.

> and agreeable people are more likely to shift their views to agree with those they are talking to

Agreeable people are more likely to shift their expressed views to agree with those they are talking to.

If they're more likely to shift their views, we call them "gullible", not "agreeable".

But this is a distinction you can't apply to language models, which don't have views.