Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Chat Notebooks

writings.stephenwolfram.com

Post reply on HN
Print view View original

21–30 of 87 posts

Re: Chat Notebooks

#21

Post by fnoof »

DigiDigiorno wrote: post #5

While I think his notebooks and features look pretty useful, he frames the article around having invented "notebooks" 36 years ago before anyone else, and talks about other notebooks not having features that they've had since 1987. This is a pretty odd context to basically describe a new chat feature. Is this a record that should be set straight? I've used Jupyter since it was IPython notebook, but I don't think that…

Theodore Gray, cofounder of wolfram research, was responsible for notebooks I believe.

> I wrote the Notebook user interface for Mathematica and led the user interface group for over 20 years.

https://home.theodoregray.com/

Re: Chat Notebooks

#22

Post by taeric »

DigiDigiorno wrote: post #5

While I think his notebooks and features look pretty useful, he frames the article around having invented "notebooks" 36 years ago before anyone else, and talks about other notebooks not having features that they've had since 1987. This is a pretty odd context to basically describe a new chat feature. Is this a record that should be set straight? I've used Jupyter since it was IPython notebook, but I don't think that…

Community may not claim to be the first with notebooks; but they certainly seem to think they have something nobody else has with it. Per their website, "The Jupyter Notebook is the original web application for creating and sharing computational documents. It offers a simple, streamlined, document-centric experience."

Which, I suppose I can cede that they are among the first "web applications" that do this. But I have a hard time really getting behind a ton of the discussion on it. Even talking about the "breadth and depth" of part of the python community is to ignore how much had been done for years in the mathematica community.

Re: Chat Notebooks

#23

Post by connordg »

One of the Wolfram/Chatbook developers here.

I'm happy to answer questions or accept feedback about the new functionality.

We're very excited about the potential of Wolfram technology + LLMs, and we've got a number of interesting projects underway in this area. Stephen's other recent blog posts linked at the top of the Chat Notebooks post provide a nice tour.

The Wolfram/Chatbook[1] package mentioned in the post is freely available for any Wolfram 13.2 users. It's also open source and available on GitHub[2].

[1]: https://paclets.com/Wolfram/Chatbook

[2]: https://github.com/WolframResearch/Chatbook

Re: Chat Notebooks

#24

Post by mnky9800n »

stabbles wrote: post #14
electroly wrote: post #12

Earlier quoted context omitted.

What's the predecessor with a notebook interface from before 1987? I'm not aware of one. Wolfram loves to claim he invented stuff but this one might actually be true. The Wikipedia article suggests a contemporary in 1987 (MathCAD) but I'm not seeing a Mathematica/Jupyter-style notebook interface before that year. That would seem to have been the year of the notebook interface, and Mathematica 1.0 did come out that ye…

Even if true it's unnecessary. I just can't read anything written by Wolfram without rolling my eyes

The only reasonable response

Re: Chat Notebooks

#25

Post by b215826 »

DigiDigiorno wrote: post #5

While I think his notebooks and features look pretty useful, he frames the article around having invented "notebooks" 36 years ago before anyone else, and talks about other notebooks not having features that they've had since 1987. This is a pretty odd context to basically describe a new chat feature. Is this a record that should be set straight? I've used Jupyter since it was IPython notebook, but I don't think that…

Notebooks are just glorified REPLs, and they've been around since the early days of Lisp.

Re: Chat Notebooks

#26

Post by digdugdirk »

connordg wrote: post #23

One of the Wolfram/Chatbook developers here. I'm happy to answer questions or accept feedback about the new functionality. We're very excited about the potential of Wolfram technology + LLMs, and we've got a number of interesting projects underway in this area. Stephen's other recent blog posts linked at the top of the Chat Notebooks post provide a nice tour. The Wolfram/Chatbook[1] package mentioned in the post is f…

Can this be released as a plain ipynb add-in/extension?

Re: Chat Notebooks

#27

Post by ComplexSystems »

connordg wrote: post #23

One of the Wolfram/Chatbook developers here. I'm happy to answer questions or accept feedback about the new functionality. We're very excited about the potential of Wolfram technology + LLMs, and we've got a number of interesting projects underway in this area. Stephen's other recent blog posts linked at the top of the Chat Notebooks post provide a nice tour. The Wolfram/Chatbook[1] package mentioned in the post is f…

What is the chat context length? Or, to be precise:

1. How long can a single chat input be? 2. If I am using a chat notebook with several previous inputs, when entering some new input below all of those, is it just appending all previous inputs together and sending the entire thing to the LLM? If so, how long can this be? Will it summarize if it exceeds that length? 3. What model is this using? GPT-3.5 or GPT-4 or something else? 4. What plans do you have next to integrate AI into Wolfram products?

Re: Chat Notebooks

#28

Post by jerpint »

connordg wrote: post #23

One of the Wolfram/Chatbook developers here. I'm happy to answer questions or accept feedback about the new functionality. We're very excited about the potential of Wolfram technology + LLMs, and we've got a number of interesting projects underway in this area. Stephen's other recent blog posts linked at the top of the Chat Notebooks post provide a nice tour. The Wolfram/Chatbook[1] package mentioned in the post is f…

What LLM are you using in the backend? Is this an openAI model or a model trained by wolfram?

Re: Chat Notebooks

#30

Post by SkyMarshal »

connordg wrote: post #23

One of the Wolfram/Chatbook developers here. I'm happy to answer questions or accept feedback about the new functionality. We're very excited about the potential of Wolfram technology + LLMs, and we've got a number of interesting projects underway in this area. Stephen's other recent blog posts linked at the top of the Chat Notebooks post provide a nice tour. The Wolfram/Chatbook[1] package mentioned in the post is f…

What is your sense on how well current AI models can handle mathematics, vs human language? Is hallucinating or inventing info a problem with math too? Do you guys do anything to minimize, mitigate, or solve it?

And do you think current AI models will be able to solve as yet unsolved problems in math and physics, perhaps with increasingly large datasets or augments like Trees of Thought or process supervision? Or do you think it will require a different fundamental model?

Post reply on HN