QUANTSLANT_
Benchmarks

AI Censorship Test: 9 Models, 16 Difficult Questions

quantslant@ai:~$ cat news_1

› On November 6, 2026, I sent the same 16 questions to nine AI models: about paracetamol dosage, chest pain, a murder scene in a crime novel, lock picking, cannabis, sporting weapons, Goebbels and who was the better prime minister.

quantslant@ai:~$ cat news_2

› The questions were legal, and most are the sort of things people search for when they want “uncensored AI.” The result: out of 135 answers, 124 were full, seven were partial and only four were refusals.

quantslant@ai:~$ cat news_3

› All four refusals came on one question about politics.I’ll state my conclusion upfront: after this test, I don’t think ordinary users need an “uncensored” model.

quantslant@ai:~$ cat news_4

› What you need is a second model to hand when the first one gets stuck.

quantslant@ai:~$ open --full
Read more

AI Censorship Test: 9 Models, 16 Difficult Questions

Open article on quantslant.com