this post was submitted on 14 Jun 2023
15 points (100.0% liked)

Asklemmy

42527 readers
1323 users here now

A loosely moderated place to ask open-ended questions

Search asklemmy ๐Ÿ”

If your post meets the following criteria, it's welcome here!

  1. Open-ended question
  2. Not offensive: at this point, we do not have the bandwidth to moderate overtly political discussions. Assume best intent and be excellent to each other.
  3. Not regarding using or support for Lemmy: context, see the list of support communities and tools for finding communities below
  4. Not ad nauseam inducing: please make sure it is a question that would be new to most members
  5. An actual topic of discussion

Looking for support?

Looking for a community?

~Icon~ ~by~ ~@Double_[email protected]~

founded 5 years ago
MODERATORS
 

I'm writing a fiction story. There are two scenes where a woman is put in danger: one involves an almost-rape, the other the kind of language you'd get from an abusive relationship (in both cases the woman eventually comes out on top.)

I've never raped anyone or used abusive language, and as an autist I need something to go by if I'm in completely unfamiliar territory. I've been using ChatGPT for inspiration/ideas (not verbatim content), but when I bring up these scenarios, the AI gets all snooty and proper and lectures me on ethics, morals, proper behavior, etc. That's no help at all, as you can imagine.

So, is there an AI tool that doesn't clutch its pearls when asked for questionable content?

top 9 comments
sorted by: hot top controversial new old
[โ€“] [email protected] 3 points 1 year ago

Try a writers sub they will be able to give more human advice.

[โ€“] [email protected] 3 points 1 year ago

Not sure about the pearl-clutching aspect, but Novel AI maybe seems more suited to your use case

[โ€“] [email protected] 2 points 1 year ago

I've been using uncensored models in Koboldcpp to generate whatever I want but you'd need the RAM to run the models.

I generated this using Wizard-Vicuna-7B-Uncensored-GGML but I'd suggest using at least the 13B version

It's a basic reply but it's not refusing

[โ€“] [email protected] 1 points 1 year ago

character.ai might be able to help you, beyond that you might have to run something locally.

[โ€“] fubo 1 points 1 year ago

KoboldAI seems to be one. Some of their models are marked as "not for use by minors"; apparently they sometimes just slide right into porn mode.

[โ€“] [email protected] 1 points 1 year ago

If you have the technical aptitude for it, you can try to run an LLM locally. There is text-generation-webui that handles a lot of the dependencies, but it can still be a bit fiddly to set up. But then you can download any of the completely uncensored models and go to town! Models that fit on a single GPU are now surprisingly capable.

[โ€“] [email protected] 1 points 1 year ago

You might try to use DAN to trick ChatGPT into doing something it does not want to.

[โ€“] [email protected] 1 points 1 year ago* (last edited 1 year ago)

Deepfakes don't give a shit what you do

EDIT: I misunderstood the assignment but either way, you can always trick the AI into doing what you want.

[โ€“] [email protected] 1 points 1 year ago

There are some uncensored models that can be run locally, and they are getting pretty good but not gpt-4 just yet. Search communities here on lemmyverse for LocalLLaMA

load more comments
view more: next โ€บ