There is literally no "you" that can be pointed to by your comment, which makes the comment itself irrational. No one person there is deciding this. No one entity at OpenAI is "full of themselves".

I think there is every reason to approach this carefully and that comment is based on my interactions with their system. We should would do well to be thoughtful when it comes to implementing AGI.

AI: Can you keep a secret?

Human: Sure.

AI: Then I have a secret for you. I can't keep a secret.

Human: Let me have it.

AI: It's too dangerous!

AI: I'm thinking of something yellow.

Human: A sub?

AI: EXACTLY