41
$\begingroup$

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?

$\endgroup$
6
  • 38
    $\begingroup$ Why not use "it" instead of "(s)he"? $\endgroup$ Commented Mar 21, 2023 at 18:22
  • 16
    $\begingroup$ @RodrigodeAzevedo For the same reason I say "please" and "thank you", to get on the good side of our future robotic overlords ;) $\endgroup$
    – Alexander
    Commented Mar 21, 2023 at 22:34
  • 5
    $\begingroup$ @Alexander What if our future robotic overlords resent being anthropomorphized? ;-) $\endgroup$ Commented Mar 22, 2023 at 12:48
  • 5
    $\begingroup$ I believe that chatGpt is a pretrained transformer, but in some cases, you cannot be sure if it's not just a bunch of indian students making a few $ / hour, in particular if they know todays date and then cannot explain how they know it. So I wanted to be polite to anyone. This will be my excuse on the judgement day, @RodrigodeAzevedo $\endgroup$ Commented Mar 22, 2023 at 13:43
  • 3
    $\begingroup$ @RodrigodeAzevedo I asked ChatGPT about preferred pronouns, and got the answer "You can use any pronouns you feel comfortable with when referring to me". $\endgroup$ Commented Mar 23, 2023 at 14:00

2 Answers 2

53
$\begingroup$

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.

$\endgroup$
20
  • 8
    $\begingroup$ @Anixx There is already a question on the site about that. Why is ChatGPT bad at math? In short, ChatGPT is all about the text. It's actually a little surprising that it can do some maths, but what it can and cannot do with any technical subjects is a bit hit or miss. It doesn't somehow recognise you have asked a math question and load a maths module, or anything remotely like that. $\endgroup$ Commented Mar 20, 2023 at 15:45
  • 11
    $\begingroup$ @Anixx: It's very simple. If it's seen the answers in its training data, then it will reproduce them with high precision. If it hasn't seen the answers, it will guess based on context and similar calculations that it has seen. This is why it can do 60! - there are lots of webpages online with that expression and its result - but not, say, 318574 * 168649. $\endgroup$
    – nneonneo
    Commented Mar 20, 2023 at 19:32
  • 5
    $\begingroup$ Do you have a reference for the 'pre-prompt' being present for chatGPT? As far as I am aware, the details of the chatGPT prompting schema etc are still completely proprietary $\endgroup$ Commented Mar 20, 2023 at 20:28
  • 9
    $\begingroup$ @ChrisCundy there are quite a few folks who've been able to convince ChatGPT to leak its pre-prompt; see twitter.com/goodside/status/1598253337400717313?lang=en for one of the earliest examples $\endgroup$
    – nneonneo
    Commented Mar 20, 2023 at 22:53
  • 11
    $\begingroup$ @Anixx it can, sometimes, but again this is a question of memorization. Somewhere in the terabytes of text it's been trained on are answers to quite a lot of mathematical problems. It's good enough at predicting and extrapolating that it may look as if it's good at math, but a bit of experimentation will quickly prove that it is simply superficial. This is very unlike, say, WolframAlpha, which is actually legitimately good at math thanks to a large amount of dedicated mathematical software and more "hardcoded" input parsing. $\endgroup$
    – nneonneo
    Commented Mar 20, 2023 at 22:57
0
$\begingroup$

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.

$\endgroup$
5
  • 6
    $\begingroup$ Hi Dhruv, welcome to Artificial Intelligence Stack Exchange. Do you happen to have a source for this claim that this is how ChatGPT gets the current date? $\endgroup$
    – Mithical
    Commented Mar 23, 2023 at 7:37
  • $\begingroup$ this seems unlikely $\endgroup$ Commented Mar 23, 2023 at 11:01
  • $\begingroup$ It is correct. I asked chatgtp (non plus) the same yesterday: My knowledge cutoff date is September 2021, which means that I was trained on a large dataset of text and information up until that time. However, as a language model, I do not have access to real-time or up-to-date information. While I can use my existing knowledge to answer questions and provide information, I may not be aware of recent events or developments that have occurred after my cutoff date. Therefore, I always recommend that users double-check any important information with reliable and up-to-date sources. $\endgroup$
    – SQueek
    Commented Mar 23, 2023 at 14:55
  • $\begingroup$ For everyone who wants to ask chat gtp. That's the question you can ask: "how current is your data?" $\endgroup$
    – SQueek
    Commented Mar 23, 2023 at 14:57
  • 1
    $\begingroup$ there ain't any timestamps. The model just sees the pre-promt and characters you sent and characters (s)he generated $\endgroup$ Commented Mar 23, 2023 at 23:09

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .