←back to thread

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

(qwenlm.github.io)
544 points tosh | 1 comments | 24 Mar 25 18:35 UTC | HN request time: 0s | 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 #
jampa ◴[24 Mar 25 19:40 UTC] No.43464682[source]▶
DeepSeek's website seems to be using two models. The one that censors only does so in the online version. Are you saying that censoring happens with this model, even in the offline version?
replies(1): >>43464723 #
1. hmottestad ◴[24 Mar 25 19:46 UTC] No.43464723[source]▶
I tried the R1 distill of llama 8B, which did refuse direct questions about the massacre.

Haven’t tried this new model locally, but I agree with you that it looks like there is a secondary censorship going on. If I ask it to list the 10 worst catastrophes of recent Chinese history with Thinking enabled then it’ll actually think about the massacre. Gets blocked very quickly, but it doesn’t look like the thinking is particularly censored.