If you still didn’t try it out, then follow the link and free up some time - it is hard to stop playing around with this thing.
From OpenAI page:
We’ve trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer followup questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests. ChatGPT is a sibling model to InstructGPT, which is trained to follow an instruction in a prompt and provide a detailed response.
To be honest, I didn’t expect it to be that good. Although, I am sure there will be incorrect/awkward/strange results in coming period. Still, the level of technology amazes.