I asked ChatGPT (3.5 and 4) about current date and (s)he answered correctly. In subsequent conversation (s)he was not able to explain how (s)he has this knowledge.
I always thought that the model only sees the conversation above and a pretrained NN is used. How is the information about current date injected into his/her knowledge?
For ChatGPT 3, the current date is inserted into a long pre-prompt, along with instructions like "this is a conversation between an AI chatbot and a human" plus "be nice" and "be truthful", which are part of the attempts to frame the next-word-predicting engine at the core of ChatGPT as a chatbot. OpenAI have confirmed this in the past, but sadly recent releases have removed that documentation.
Inherently, the core of ChatGPT - the GPT large language model - is not a chatbot. It has some resemblance conceptually to an image inpainting system — it predicts text that is likely, given preceding text.
I expect the same is true of ChatGPT 4, but have not seen any confirmation of this. It is feasible in principle to alter architecture of the bots to have them reference external data sources, but I believe that for the current date, a pre-prompt will still be in use.
Old link to OpenAI's confirmation - sadly no longer available - https://platform.openai.com/docs/guides/chat/instructing-chat-models - if anyone has link to archived copy please let me know in the comments.
As an AI language model, ChatGPT does not have access to real-time information unless it's provided to it. Its knowledge cutoff date is September 2021. Therefore, it actually relies on the timestamp of the user's message to give the current date. Based on the user's message's timestamp, it assumes the current date. For example 2023-03-23 10:10:00 UTC.
