read this! was a cool paper—we wanted to also create an agent similar to the one they talk about in the paper to discover censored topics. Theres a wip one in Seer where it tries to validate if the models know the censored facts https://github.com/ajobi-uhc/seer/tree/main/experiments/china-facts-investigation
read this! was a cool paper—we wanted to also create an agent similar to the one they talk about in the paper to discover censored topics. Theres a wip one in Seer where it tries to validate if the models know the censored facts https://github.com/ajobi-uhc/seer/tree/main/experiments/china-facts-investigation