Here's a demo of some system prompt engineering which resulted in better results for the older ChatGPT: https://github.com/minimaxir/simpleaichat/blob/main/examples...

Coincidentially, the new gpt-3.5-turbo-0613 model also has better system prompt guidance: for the demo above and some further prompt tweaking, it's possible to get ChatGPT to output code super reliably.