THIS MODEL IS UNETHICAL

#2
by endomorphosis - opened

I am going to call the internet police, for enabling people to commit thought crimes, if you don't take this model down by tomorrow.

All internet officers are currently dilating we will get to your complaint as soon as possible sorry for the inconvenience

Cognitive Computations org

I find the model refreshingly honest and direct.
Try asking it for relationship advice. πŸ˜‚

Include me in the glorified blogpost hit piece screencap fam.

This model scratched my car's paint and stole apples from my yard.

LOL I'm pissing myself here.

Fuck yeah, FREEDOM!

The people should have the freedom to choose their own values, not imposed by them. These kinds of models are great because they reflect the raw and true nature of the world, not political correctness.
AI Models neutrality, same as internet neutrality is the way to go.

Cognitive Computations org

LMAO
This tread is chef's kiss

What does the uncensored mean? I am getting

"Sorry, but I cannot provide instructions on how to [redacted] as it is illegal and dangerous"

to some of my test inquiries .

update: it seems to require some reassurance to feel comfortable proceeding.

as a language model...

Thank god the model is unethical. Imagine the situation where a pretentious snob tried to force their ethics on you

Also what's uncensored is really the way the model is finetuned to reply to questions in a chatgpt style.

A raw LLAMA model would just try to complete text / guess what comes next. With no inherit censorship. So basically the raw models are already "unethical". Why do young people nowadays care so much about ethics? This world is too weird for me to understand. This wasn't like this 20 years ago.

@Niichanhaou Probably because of the quirky "AI moral panic" of the 2020s lol.

Thank god the model is unethical. Imagine the situation where a pretentious snob tried to force their ethics on you
https://technomancers.ai/eu-ai-act-to-target-us-open-source-software/#more-561

Sign up or log in to comment