I felt the default GPT-5 responses were neutral. I checked and it hasn't yet emitted any emojis or exclamation marks, even though I used some in my replies. When I asked for a review of my question it focused on my query rather than me.
Will need to test longer contexts though - I've noticed Sonnet 4 becomes a bit less stoic and more friendly in some longer chats, but maybe it's just reflecting my casual language back at me.
* It feels a bit more competent, as if it had more nuance or detail to say about each point.
* It got a few obscure details about OpenBSD correct right away - both Sonnet 4 and 4o sometimes conflate Linux and OpenBSD commands.
* It was fun asking GPT-5 to not only answer the query, but also to provide a brief analysis of the query itself for insights into myself!
Not a detailed review, but just a couple things I noticed with some limited usage.