Built as an online assistant that can talk back-and-forth with a user. Its creator, OpenAI, described ChatGPT by saying, "We have trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer follow-up questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests."

One important thing to note when trying to understand ChatGPT is that it does not understand what it is composing. Instead, the chatbot is guessing the most likely word that follows the previous word, and the most likely word after that, and so on. 

What are the limitations of ChatGPT?

The model can create sentences that are plausible, but don't make sense.  

The tool can answer one way based on the construction of the query, and then when that query is tweaked, it may give a different answer. 

The model tends to be verbose.

The model does not ask clarifying questions but instead makes a guess at what the questioner is asking for.

The developers have also included an important intentional limitation: "While we have made efforts to make the model refuse inappropriate requests, it will sometimes respond to harmful instructions or exhibit biased behavior. We’re using our Moderation API to warn or block certain types of unsafe content, but we expect it to have some false negatives and positives for now."

This is an overview of ChatGPT by Matthew Frenkel from New York University.