They finished training GPT4 mid last year, before ChatGPT was released
I enjoy the ChatGPT jailbreaking scene, and almost every time there's a significant break found, within a day, ChatGPT will dance around it (take the big token-leak jailbreak from a few days ago.) The GPT4 model may not be retrained itself, but it seems fairly evident that the ability for supplemental rules/fine-tuning is baked into their architecture for ChatGPT.