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

41–50 of 87 posts

Re: Chat Notebooks

#41

Post by cshimmin »

akiselev wrote: post #7
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…

> Is this a record that should be set straight? It's Wolfram. If they didn't claim to invent something fundamental in the first paragraph, I'd immediately assume the site was hacked or it's a poorly timed April fools joke written by an intern.

Yes, he is a narcissist. Smart guy, cool products, but it's just like how Trump cannot talk about anything without shoehorning in a statement like "I got more votes than any sitting president ever" when being asked about something completely unrelated.

My favorite example is when Caltech put out a press release about a young woman got her PhD and nearly beat Wolfram's record for youngest PhD from Caltech. He felt immediately compelled to write a long winded several-thousand word essay about how glad he is to still have the record for being the youngest PhD, by a full two weeks! And also, he wanted to remind everyone that he knew Richard Feynman. Cringe...

Re: Chat Notebooks

#42

Post by meghan_rain »

All I want is a self-hostable open-source GPT4.

The community will come up with things that will make the content of this blog post look like hello world todo apps.

Can't a wealthy bazillionaire like Elon Musk just drop a few billions and buy the rights to GPT4?

Re: Chat Notebooks

#43

Post by williamstein »

paulgb wrote: post #13
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…

> I've used Jupyter since it was IPython notebook, but I don't think that community claims to be the first coming of notebooks. My recollection (which could be wrong, it's been a while) is that SageMath’s notebook preceeded iPython notebooks. IIRC iPython started as a CLI repl, which may have come before the notebook. (Mathematica came before all of them, and likely inspired SageMath’s interface)

Tom Boothby, Alex Clemesha and I wrote the first web based notebook interface in 2006, which was indeed the Sage Notebook. It was very painful at the time - jquery wasn’t even a thing yet! It was inspired by Mathematica notebooks, mainly because Alex was a heavy Mathematica user when he was a physics undergrad at UCSD. Similarly, Fernando Perez’s Ipython CLI was also inspired by Mathematica notebooks. I personally didn’t use Mathematica notebooks a lot, and was even more inspired by various clever Emacs modes and also Mathcad, and by the first version of Google docs. In any case, we were all inspired by Mathematica notebooks!

Re: Chat Notebooks

#44

Post by TOGoS »

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…

> There’s another important difference too. In an ordinary Notebook there’s a “temporal thread of evaluation” in which inputs and outputs appear in the sequence they’re generated in time

I've always found this kinda confusing, and the "evaluate everything above" approach used by the LLM cells much more intuitive, but having the two types of cells behave so differently brings it back to confusing and asking for trouble. Do you think it would make sense to have an option to force all cells to work that way?

Re: Chat Notebooks

#45

Post by williamstein »

taeric wrote: post #22
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 hav…

They do say what you quote with those words, but I think their intention is just trying to clarify the difference between Jupyter classic and JupyterLab. The Sage notebook predates the Jupyter project by at least five years, but was visually and functionally very similar.

Re: Chat Notebooks

#46

Post by lurker137 »

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…

Will the notebook feature allow branching out from the linear chain of chats or even reverting the chain to an earlier point? It wasn't clear from the post

Re: Chat Notebooks

#47

Post by shaunxcode »

detourdog wrote: post #9
Yhippa wrote: post #3

I love the concept of notebooks (as referred to in this article). It reminds me of the way HyperCard made it very easy for non-techies to create something that looks great to share out with the world. I'm honestly surprised nobody else has exploited this functionality before!

At that time FileMaker was the HyperCard for data analysis. They could also interoperate.

No one asked but the MacIvory genera world could also interoperate with HyperCard.

Re: Chat Notebooks

#48

Post by canadianfella »

akiselev wrote: post #7
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…

> Is this a record that should be set straight? It's Wolfram. If they didn't claim to invent something fundamental in the first paragraph, I'd immediately assume the site was hacked or it's a poorly timed April fools joke written by an intern.

[dead]

Re: Chat Notebooks

#50

Post by oslac »

Hard to believe people look at this Chat UX with LLMs as a good interface. Look at the amount of blabbering in the example - why?
Post reply on HN