It is also in that sour spot where it is completely closed, which might be fine (GPT-4, Claude 2) if it was much better than the open-source models, but that does not seem to be cut-and-dry: https://huggingface.co/openchat/openchat_3.5#comparison-with...

Do we know on what it's been trained on? I'm having a hard time believing anything trained on tweets would yield anything useful.