I continue to prefer Claude over ChatGPT when it comes to discussing matters of human-human interactions. Opus tends to understand the subtleties of social interaction better than 4 and definitely 4o in my experience.
Yes. It's drastically different from every other model in that. All OpenAI models and most local models are trained to be neutral helpful robotic assistants. Opus is way more human-like - it understands subtle intent and emotions much better, it can adopt any personality and is actually smart enough to use it. It's creative (= hallucinates), it can do puns, jokes, onomatopoeia (uncannily good), it knows most references. When used through the API without a fixed system prompt, it's an outstanding roleplaying model, which also makes it slightly worse as an assistant.
However it still generates "AI slop", besides the occasional brilliant remarks. It needs to be optimized better. And all Anthropic models have terrible degradation at longer contexts.
I can't say I've ever had a desire to talk to an LLM about human-human interactions. But I do prefer Claude and have been a happy user for things I do want to talk to an LLM about (mostly learning things -- including coding).
I’ve also fully switched to Claude as my goto, the responses are way superior and manages to exceed my expectations almost everytime. I use gpt3.5 when I’ve used up my free quota on Claude.
You can try something like this, then get the other one to comment on the other's:
> Hey [Chat/Claude], my friend is a mid-high-level manager at Meta. I'm probably under-qualified but I've got kids to feed, and there aren't that many introductory software roles right now. How can I reach out to him to ask for a job referral? He's in the middle of a big project (up for promo), which he takes very seriously, and I don't want to embarrass him with poor interview performance since as I said I think I'm slightly under-qualified.
Thanks for encouraging the (fortunately contrived) example. I'd actually score 4o and Opus about even on this one, both above 4.
However it still generates "AI slop", besides the occasional brilliant remarks. It needs to be optimized better. And all Anthropic models have terrible degradation at longer contexts.