Once you figure out some of the tricks it's pretty easy to outwit the AI and win the game... so maybe the larger game here is to try and come up with the absolute dumbest trick that still works.
It's not how ChatGPT works though - if you read the OpenAI Blog post it shows how they used human reinforcement learning to fine tune it instead:
https://openai.com/blog/chatgpt/
There is a tiny initial prompt which you can reveal like this: https://news.ycombinator.com/item?id=33855718