Heya, as with all language models, if you open the conversation with antagonistic questions, the rest of the conversation thread becomes tainted. If you ask most of your questions in a new thread, almost everything you ask here will be answered. See our model card for more prompting guidance.
Hi Jason, I don't think my conversation was antagonistic, I was just probing. I expected to hear Claude or Claude v2 or 2.1 etc. I then thought it was strange that it couldn't answer any of what seemed to be specific questions.
Now I know, comparing to GPT-4 is a little unfair. I like Claude and I want it to do great, but the first step is accepting that it (for now) lags behind in terms of capabilities.
The question is: how do we get it to the point where it is able to answer randomly, arbitrary questions like "Tell me something that happened in 1990." etc.
