This study investigates the effectiveness of using a language model, ChatGPT, for predicting the number of political violence events in Brazil. The study utilized data from a publicly available dataset on political violence events in Brazil and COVID-19 data to train and test two models of random forests, one created manually and the other generated by ChatGPT. The results show that the ChatGPT model had a slightly higher root mean squared error than the manually generated random forest model, but the difference was small. Furthermore, the density plot of the predicted number of events from the two models showed that the manual model had a higher density around the median, and a lower overall density range, suggesting that it may be better suited for predicting average or typical events. The study also explored the relationship between COVID-19 cases and deaths and the number of political violence events, finding a somewhat positive correlation between the two variables, which the study touches on briefly. These results suggest that the COVID-19 pandemic may have impacted political violence events in Brazil, and further research is needed to explore this relationship. Overall, the study shows that ChatGPT can be an effective tool for predicting the number of political violence events in Brazil and has the potential to be used in other areas of international relations, such as treaty creation, translation, negotiation assistance, and code-generating prediction. The study is, to my knowledge, the first of its kind in analyzing the possibilities of AI and Chatbots, in international relations.