Comment by automationist
6 months ago
If anyone's wondering, here's a short sample. It quietly updated last night, and I ended up chatting for like an hour. It sounds as smart as before, but like 10x more emotionally intelligent. Laughter is the biggest giveaway, but the serious/empathetic tones for more therapy-like conversations are noticeable, too. https://drive.google.com/file/d/16kiJ2hQW3KF4IfwYaPHdNXC-rsU...
I find it weird the way it's just lying. Did you tell it to impersonate a living human?
Obviously I get LLMs have no concept of truth and hallucinate all the time, but I would have thought that the model prompt would have told it to acknowledge that it's a chatbot.
Holy moley. Thanks for sharing. I had to work with the API version a lot the last week and it was frustrating how "old" it felt intelligence-wise. This is in another league, I hope it's 4.1 x audio training, I'd love to talk to this. Current one is passable for hands-free RAG, that's it for me.
Did it really say partwheel or is it garbled?
It sounded like partwheel to me too. Now I wonder if more people will hear it as partwheel due to the McGurk effect [0].
[0] https://en.wikipedia.org/wiki/McGurk_effect