What it cannot do
While ChatGPT was successful to generate R code for a single dose
simulation, our experience showed that it struggled to provide an
appropriate code for simulating multiple doses of FVIII and the results
it generated were unrealistic. Therefore, caution must be exercised when
using R codes generated by ChatGPT in pharmacometrics. We also asked
ChatGPT to produce NONMEM code for the same model. Although the produced
code did resemble a NONMEM control stream, the produced file contained
multiple errors and redunancies, and failed to run.