343
Now that you've all tried it ... ChatGPT web traffic falls 10% (www.theregister.com)
submitted 3 years ago by [M, B] to c/technology@lemmy.world
118 comments fedilink hide all child comments
 

Slow June, people voting with their feet amid this AI craze, or something else?

you are viewing a single comment's thread
view the rest of the comments
[–] 5 points 3 years ago (4 children)

I have a number of language models running locally. I am really liking the gpt4all install with Hermes model. So in my case i used chatgpt right up untill i had one i could keep private.

  • permalink
  • fedilink
  • source
  • hideshow 4 child comments
    •
  • [–] 4 points 3 years ago (1 child)

    How does it compare with ChatGPT (GPT 3.5), quality and speed wise?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 2 points 3 years ago

    Depends how you get in accomplished if you use the python bindings its slow but using the gpt4all its quick and there is a gpt4all api should you wish to build a private assistant. I like that one but its still run by a company so mileage may vary there are a few projects on github for use with opensource models. I can get better quality from the hermes model than i can with GPT 3.5 IMO but some models are better than others in regards to what you are trying to do. If you have done any work with stable diffusion lots of different models are popping up right now for different use-cases like you see on civit.ai. A good coding bot is probably going to be a bit shit in a conversation.

  • permalink
  • fedilink
  • source
  • parent