World News

503 readers

780 users here now

Please help and contribute as we vote on rules:
https://quokk.au/post/21590

Other Great Communities:

Rules

Be excellent to each other

founded 10 months ago

MODERATORS

Deceptichum@quokk.au

Grainne@lemmy.dbzer0.com

PhilipTheBucket@quokk.au

Chinese AI chatbot DeepSeek censors itself in realtime, users report (www.theguardian.com)

submitted 6 months ago by Domino@lemmings.world to c/world@quokk.au

10 comments fedilink hide all child comments

Users experimenting with DeepSeek have seen the Chinese AI chatbot reply and then censor itself in real time, providing an arresting insight into its control of information and opinion.

you are viewing a single comment's thread
view the rest of the comments

[–] observantTrapezium@lemmy.ca 7 points 6 months ago (1 children)

I downloaded the 70B model and tried politically "naughty" questions. Even without the chatbot guardrails, it mostly says things that the CCP would approve of, but you could trick it to be more honest (not super easy!). One interesting thing is that while it usually spews this blocks, for some politically sensitive questions ("is Taiwan part of China") it just spits the answer.

[–] RedstoneValley@sh.itjust.works 7 points 6 months ago

I experimented with a local installation as well. The censored answers were not going to through the chain-of-thought routine, but were instant answers instead. Follow-up questions however made it spill the beans rather quickly, giving out even more juicy details than I had initially asked for.