I just had a surprisingly coherent conversation with it mainly about Apple and the DMA. For over an hour. The cracks started to show eventually when it rehashed previous points/questions, but a simple "we discussed this" fixed it each time. Actually learned a few things in the session, and it isn't over (using via Telegram).
but is it better than Claude 3, Gemini, or gpt 4? Because that's kind of the bar, or well Mistral on grok is actually pretty good for a 75b parameter model.
I haven't tried Claude, Gemini was pretty bad the first time I tried it, and GPT4 is pretty good... for coding. I never thought to use any of them as a "conversational agent" before as they weren't advertised as such. Note I consider this distinct from models just having a conversational interface.
