←back to thread

Qwen2.5-VL-32B: Smarter and Lighter

(qwenlm.github.io)
544 points tosh | 2 comments | 24 Mar 25 18:35 UTC | HN request time: 0.001s | source
Show context
hmottestad ◴[24 Mar 25 19:36 UTC] No.43464637[source]▶
Just don’t ask it about the tiananmen square massacre or you’ll get a security warning. Even if you rephrase it.

It’ll happily talk about Bloody Sunday.

Probably a great model, but it worries me that it has such restrictions.

Sure OpenAI also has lots of restrictions, but this feels more like straight up censorship since it’ll happily go on about bad things the governments of the west have done.

replies(7): >>43464653 #>>43464682 #>>43464747 #>>43464832 #>>43466474 #>>43466816 #>>43468343 #
generalizations ◴[24 Mar 25 19:37 UTC] No.43464653[source]▶
Nah, it's great for things that Western models are censored on. The True Hacker will keep an Eastern and Western model available, depending on what they need information on.
replies(3): >>43464743 #>>43464802 #>>43464979 #
1. hmottestad ◴[24 Mar 25 19:48 UTC] No.43464743[source]▶
I tried to ask it about Java exploits that would allow me to gain RCE, but it refused just as most western models do.

That was the only thing I could think to ask really. Do you have a better example maybe?

replies(1): >>43467640 #
2. OkGoDoIt ◴[25 Mar 25 02:38 UTC] No.43467640[source]▶
Adult content and things like making biological/chemical/nuclear weapons are the other main topics that usually get censored. I don’t think the Chinese models tend to be less censored than western models in these dimensions. You can sometimes find “uncensored“ models on HuggingFace where people basically finetune sensitive topics back in. There is a finetuned version of R1 called 1776 that will correctly answer Chinese-censored questions, for example.