It is instruction-tuned with very flatly-written responses. That makes the structure of the response more informative and less playful.
Personally I like the no-bullshit approach, but you could also fine-tune a personality if you wanted.
Personally I like the no-bullshit approach, but you could also fine-tune a personality if you wanted.
https://huggingface.co/models?sort=modified&search=chronos
Or Samantha
In my experience, it just makes it harder to extract useful information.
Some are more visual and others have learning disabilities. I think that ChatGPT is too uniform and if it was fine-tuned towards you personally that would be the best version