this post was submitted on 27 Jun 2023
11 points (100.0% liked)

Chat

7499 readers
16 users here now

Relaxed section for discussion and debate that doesn't fit anywhere else. Whether it's advice, how your week is going, a link that's at the back of your mind, or something like that, it can likely go here.

Subcommunities on Beehaw:

This community's icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.

founded 2 years ago
MODERATORS
remington
alyaza
11
What are some good uses we can do/make with ai and such? (lemmy.fmhy.ml)
submitted 1 year ago by QuietStorm@lemmy.fmhy.ml to c/chat
11 comments fedilink hide all child comments
 

sense ai is still trending, what acatly can we do with them that might be useful. ive been using chatgpt for code but the best thing ive got so far is something like pong, i would code myself but i find it way too hard for my brain and i struggle with almost everything. i feel like i could do more with ai but im not sure what.

got any idea or what have you been doing with ai tools?

you are viewing a single comment's thread
view the rest of the comments
[–] fiasco@possumpat.io 6 points 1 year ago (1 children)

I've used it a bit to try and work on my Spanish. That is, using it as a sophisticated chatbot. Unfortunately it's still quite frustrating for that: I figured I'd ask it to play un juego de rol (a roleplaying game), and it kinda sucks at it. I'm gonna give it a go with an open source alternative, hopefully they're less aggressively calibrated toward being tedious and awful. It's just, getting an open source language model running takes a decent amount of time and effort, so I'm sorta midway through that.

[–] CreativeTensors 1 points 1 year ago (1 children)

Have you checked out something like https://github.com/serge-chat/serge? It's changed a bit since I installed it, but I remember it being pretty quick to set-up.

[–] fiasco@possumpat.io 3 points 1 year ago

At the moment I'm trying https://gpt4all.io/index.html, a big part of the problem is that I just haven't had a lot of time to deal with it, and the model parameter files are large downloads.