This censorship is pretty interesting. Reading the post it also makes me wonder, are different censors provided depending on input language? Different models served to different regions? This can also get complicated due to the stochastic nature of model output, though the linked tweet appears to be post generation filtering. It's much harder to determine generation based filtering especially if done in subtle ways like just reducing the probability.
I don't think this behavior is just limited to Chinese based models fwiw. A lack of transparency makes this space difficult to navigate. Though maybe the saving grace is that filtering is very hard, even meaning that it is hard to entirely remove certain subjects from pretraining data. (Have fun going through 10s of trillions of tokens)
This censorship is pretty interesting. Reading the post it also makes me wonder, are different censors provided depending on input language? Different models served to different regions? This can also get complicated due to the stochastic nature of model output, though the linked tweet appears to be post generation filtering. It's much harder to determine generation based filtering especially if done in subtle ways like just reducing the probability.
I don't think this behavior is just limited to Chinese based models fwiw. A lack of transparency makes this space difficult to navigate. Though maybe the saving grace is that filtering is very hard, even meaning that it is hard to entirely remove certain subjects from pretraining data. (Have fun going through 10s of trillions of tokens)