I wonder how much of this is due to reliance on Twitter data. Or even just RLHF from humans that have a preference for Twitter style information.
I wonder how much of this is due to reliance on Twitter data. Or even just RLHF from humans that have a preference for Twitter style information.
I don't think it's twitter. My guess would be that it's been trained for conciseness as way to improve token efficiency in the same vein as caveman.