[orbital-decay]

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.