is no longer whether AI can write code, but whether we can trust the code it writes? Over the past few years, ChatGPT and other large language models have become increasingly common in the daily workflow of students, analysts, researchers, and data scientists. Many of us have already used AI tools to generate a Python function, debug an error message, automate a repetitive task, or quickly translate code from one language to another. But there is a major difference between asking ChatGPT to write a small helper function and asking it to implement a complex econometric method. Can ChatGPT correctly code a Difference-in-Differences model? Can it implement Inverse Probability Treatment Weighting? Can it reproduce a Regression Discontinuity analysis? Can it do this not only in Python, but also in R and Stata? That is why the article “Can AI write your code? A case study of ChatGPT’s statistical coding capabilities for quantitative research” by Winberg et al. immediately caught my attention.…