I haven’t tried this yet, but I have a feeling that it would fail for anything nontrivial. Nevertheless, the concept is very interesting, and as soon as I get API access to GPT-4, I will try it.
I’ve recently ported a library from TypeScript to Python with the help of ChatGPT (GPT-4), and it took me about a day. It would be interesting to run this tool on the same codebase and compare the results.
If anyone has GPT-4 API access, I would really appreciate if they tried running this tool on something simple, and wrote about the result in the comments.
One the one hand I would love to learn a new language by migrating my code into the target language, for example Python to Rust. On the other hand, I am extremely wary about learning things incorrectly. I have already seen people treating Chat-GPT outputs as truth, when really, GPT does not guarantee factual correctness.
Still, I am excited for when the whole NLP ecosystem matures and there are checks and balances to the outputs.