←back to thread

Bypass DeepSeek censorship by speaking in hex

(substack.com)
755 points MedadNewman | 1 comments | 31 Jan 25 19:41 UTC | HN request time: 0.205s | source
Show context
ks2048 ◴[31 Jan 25 20:16 UTC] No.42891407[source]▶
Part of the blog is hypothesizing that the censorship is in a separate filtering stage rather than the model itself. But, the example of hex encoding doesn't prove or disprove that at all, does it? Can't you just check on a version running open-source weights?
replies(2): >>42891485 #>>42891489 #
1. pomatic ◴[31 Jan 25 20:23 UTC] No.42891489[source]▶
The open source model seems to be uncensored, lending weight to the separate filter concept. Plus, any filter needs to be revised as new workarounds emerge - if it is baked in to the model that requires retraining, whereas it's reasonably light work for a frontend filter.