this post was submitted on 08 Jul 2023
344 points (97.5% liked)

Technology

62044 readers
4055 users here now

This is a most excellent place for technology news and articles.

Our Rules

  1. Follow the lemmy.world rules.
  2. Only tech related content.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

founded 2 years ago
MODERATORS
L3s
enu
technopagan
L4s
344
Now that you've all tried it ... ChatGPT web traffic falls 10% (www.theregister.com)
submitted 2 years ago by L4s to c/technology
103 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
[–] gaiussabinus 5 points 2 years ago (2 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.

[–] [email protected] 4 points 2 years ago (1 children)

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

[–] gaiussabinus 2 points 2 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.

[–] elskertesla 2 points 2 years ago (1 children)

How do I get started with the models you are mentioning?