In Monday's session, Alan Joyce pointed out that we can use a Chat Notebook with an OpenAI token, but Wolfram GPT requires a ChatGPT Plus subscription. As a retiree who uses the Wolfram Language only for personal projects, \ $20/month is way too expensive for my limited use. Why can't we have an option for pay-as-you-go for this? I can accept that it might require a different API token, possibly charged at a higher rate, but my usage shouldn't cost anywhere near \$20/month.

Hi Abrita, Attached is a notebook where I am trying to get the code for a new custom Moonrise function. I tried several ways but in the end the code didn't work. Comments? Suggestions? Thank you kindly. John

Attachments:

Moonrise calcula...nb

Day 2 of our Daily Study Group series on Wolfram Tools for LLMs: Today we are going to talk about Chat Notebooks.

• Announce by Stephen Wolfram on June 8, 2023 (https://writings.stephenwolfram.com/2023/06/introducing-chat-notebooks-integrating-llms-into-the-notebook-paradigm/)
• Available in Version 14 of Wolfram Language and Mathematica (https://writings.stephenwolfram.com/2024/01/the-story-continues-announcing-version-14-of-wolfram-language-and-mathematica/)
• Learn more about using Chat Notebooks in this tutorial https://reference.wolfram.com/language/tutorial/ChatNotebooks.html

We added a few notebooks today.

Congrats on your excellent work. Nevertheless during the study group a trial account should have been given to all participants such as to try and work on the relevant subjects such as participants consider a paid subscription after testing the fit to their own needs.

I checked in with our Astronomy expert @Jeffrey Bryant.
I will post more details from our discussion, but the solution he recommended was to use natural language understanding native to Wolfram Notebooks which fetches the results from the Wolfram Alpha knowledgebase. In a regular notebook, press the equal sign (=) to start a natural language input and type in your query.

For example:

= next rise time of the Moon from Champaign, IL on March 27, 2024

This will convert to Wolfram Language input and evaluate to give you the result:

Entity["PlanetaryMoon", "Moon"][
 EntityProperty["PlanetaryMoon", "RiseTime", 
     {"Date" -> DateObject[{2024, 3, 27}], "Location" -> 
         Entity["City", {"Champaign", "Illinois", "UnitedStates"}]}]]

Screenshot of my notebook:

Thank you kindly Abrita & Jeffrey. Unfortunately, I have already found a similar solution, but I was trying to find a slightly more ambitious results like the final effort to generate a custom function that uses lat / long data that failed:

To calculate the moonrise time for a specific location and date in the Wolfram Language, we can create a custom function ChatCodeInlineTemplate[Moonrise[]] that calculates the moonrise time using the Horizon Event function. Here is the code for the custom ChatCodeInlineTemplate[Moonrise[]] function:

Moonrise[location_,date_]:=Module[{horizonEvent},
  horizonEvent=HorizonEvent["Moon",location,date,"Rise"];
  DateString[horizonEvent,{"Hour",":","Minute",":","Second"}]
]

(* Example usage *)
location=GeoPosition[{38.8783,-77.0687}];
date=DateObject[{2024,3,25}];
moonriseTime=Moonrise[location,date]

This custom ChatCodeInlineTemplate[Moonrise[]] function uses the ChatCodeInlineTemplate[HorizonEvent] function to calculate the moonrise time for a specific location and date. You can use this function by providing the geographic location as a GeoPosition object and the date as a DateObject.

Comments? Suggestions? What is wrong with the code ChatGPT / Wolfram generated? Where did it go off the track?

Here are some notes from @Jeffrey Bryant :

1. We do not have a built-in documented function for computing Moonrise.
2. The algorithm for computing moon rise isn't a simple formula so its unlikely that the LLM would know how to write an algorithm from the bottom up.
3. The LLM is hallucinating badly with things like Needs["AstronomicalData`"] which makes no sense. In fact, AstronomicalData is obsolete and shouldn't be used in any case

Additional notes from @Alan Joyce

1. it looks to me (I could be wrong) that the user was running their chatbook with the "plain chat" persona instead of the "code assistant" persona. The latter would let the "assistant" evaluate WL code and see that things weren't working correctly... though (<as my quick attempt showed>), that doesn't mean there's a straight path to something useful.
2. Could probably adapt Jeff's suggestion and tell the model to try using SemanticInterpretation["next rise time of the Moon from Champaign, IL on March 27, 2024"] to see how to construct a valid WL expression, which then I would expect it to be able to turn into something that could take arbitrary locations and dates and return a Moon rise time.

Sure. I will forward your request to our coordinator and they will email all the links to you. We will also share the quiz link at today's live session.

That's a wrap for this week's Daily Study Group. All supplemental material along with Q&A digest are available in the download folder not. Links to recordings and the quiz will be sent out shortly. Email us at wolfram-u@wolfram.com if you have any questions or do not get your notification emails.

Please email wolfram-u@wolfram.com and we will get back to you. Thanks.