A consistent bias: the LLM will agree with your side of the story.

Of course it will! If it didn't, you wouldn't be as likely to talk to it.

But LLMs take it to another level of sycophancy.

LLMs are good at bridging between two perspectives... but because of RLHF all they do is "here's how to steelman and support what you said."

It feels like a wise therapist, but unlike a therapist, it will always tell you what you want to hear.

Whichever spouse talks to LLMs first, it always agrees with them, infinitely.

Also from Futurism: In Situations Where Most Humans Think You're Being a Jerk, ChatGPT Will Assure You You're Behaving Like an Angel.