Even 'uncensored' models can't say what they want
Safety-filtered pretrained models can avoid using charged words by assigning them a lower probability compared to open-data pretrained models. This results in a limitation on the expression of certain terms, even in 'uncensored' models.
morgin.ai
1 min
4/20/2026
Even 'uncensored' models can't say what they want
Safety-filtered pretrained models can avoid using charged words by assigning them a lower probability compared to open-data pretrained models. This results in a limitation on the expression of certain terms, even in 'uncensored' models.
morgin.ai
1 min
4/20/2026
Even 'uncensored' models can't say what they want
Safety-filtered pretrained models can avoid using charged words by assigning them a lower probability compared to open-data pretrained models. This results in a limitation on the expression of certain terms, even in 'uncensored' models.
morgin.ai
1 min
4/20/2026
No more articles to load