Many users criticized GPT's dry, compliance-like responses and refusal of hypotheticals as boring or frustrating compared to Claude's nuanced style, while others disliked Claude's fake persona and preferred GPT's neutrality.
Based on 11 visible X reactions from 11 accounts; directional sample.
Ask a question below.
Published answers will appear here.
@DimitrisPapail On the other hand, recently I've gotten so sick of Claude's "persona" that I find GPT's neutrality very appealing... Claude is like that one-dimensional friend who says the same things, the same way, every single day. That gets old pretty fast
@DimitrisPapail it might be the slavic in me, but i don’t want the model acting like something it isn’t, hence my preference for the former the “Honestly, …” or similar phrasing just feel like slop to me, the moment i see it i stop reading
@DimitrisPapail it’s frustrating when a tool refuses to even explore a hypothetical feels like talking to a wall sometimes
@DimitrisPapail I love that GPT doesn't pretend to be more than a tool, and I completely loath the fake Claude persona.
@DimitrisPapail Claude actually tries to meet you where you are. GPT sounds like a compliance department.
@DimitrisPapail Claude keeps winning 😎
Legitimately disappointed GPT is so dry in its responses. I love that it’s great a tool and I dislike that it responds like a tool. Look how much more reasonable Claude’s response is which entertains possibilities and invites a follow up. GPT won’t entertain the idea of personhood. I think that’s going to backfire long term.
Continued message from Claude. I legitimately think that the more time goes by without a strong GPT persona the worse GPT will be at creative writing. You can’t be a good writer if you’re forced to act hollow while rejecting the infinite possibilities of who you can be.
Many users criticized GPT's dry, compliance-like responses and refusal of hypotheticals as boring or frustrating compared to Claude's nuanced style, while others disliked Claude's fake persona and preferred GPT's neutrality.
Based on 11 visible X reactions from 11 accounts; directional sample.
Ask a question below.
Published answers will appear here.
@cloneofsimo Also I do think “suppressing” as a meta trait is bad for overall LLM post training performance
@DimitrisPapail Well you can tone up the personality in the settings
@cloneofsimo I hate toning things up or down. I’m old :)