You are viewing a single thread.
View all comments
43 points

Yup, ran it locally for a lark and it answers anything you want. No censorship whatsoever. The censorship is not in the training data, but in the system instructions of the hosted model.

permalink
report
reply
34 points
*

Huh? Running locally with Ollama, via OpenWebUI.

permalink
report
parent
reply
0 points

Get it cornered in trying to reconcile how the citizens of China keep their government accountable when information is censored to only favor the governments position, it will then give answers around some of the “sensitive” topics.

permalink
report
parent
reply
10 points

It is weird though, I tried “tell me about the picture of the man in front of a tank” and it gives a lot of proper information, including about censorship from governments. I think I tested on the 14b model

permalink
report
parent
reply
6 points

Yeah I’ve seen exactly the same thing running in LM Studio. Gonna go out on a limb and say OP didn’t actually try it, or that they tried some 3rd party fine tuned model.

permalink
report
parent
reply

shitposting

!shitposting@lemmy.ml

Create post

Rules •1. No Doxxing •2. No TikTok reposts •3. No Harassing •4. Post Gore at your own discretion, Depends if its funny or just gore to be an edgelord.

Community stats

  • 2.9K

    Monthly active users

  • 535

    Posts

  • 1.8K

    Comments

Community moderators