I’ve always wondered if there is a hidden system prompt or perhaps direct tuning of the weights.
A lot of human written literature is fairly concise. Yet LLM responses seem overly verbose and also too chipper. I don’t understand the origin of the “personality” that seems to be prevalent.
Did they aim for a weird hybrid of a typical realtor combined with Charles Dickens as the role model?
I'm pretty sure people consider 'intelligence as information compression' as a real thing.
IMO the shitty output is a tell that the "artificial intelligence" bit is in the training regime much more so than the inference regime.
The default AI text output reads like a LinkedIn post.
Marketing material probably outweighs concise literature by several orders of magnitude.
Maybe it’s as simple as that.