On: Bypass DeepSeek censorship by speaking in hex

[throw_pm23]

But did this beat the censorship though? It actually said what an Oxford student could plausible say. So it is not "his opinion", he does not "endorse it", etc. I find this to be different from saying it "with conviction", so maybe the censors are fine with this but not the other.

[anvuong → throw_pm23]

What's the difference? LLMs confidently lie or produce incorrect results all the time, with "conviction".

[prisenco → throw_pm23]

I'm confused. You want the unfiltered opinion of the model itself? Models don't have opinions, they don't work that way.