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

81–87 of 87 posts

Re: Chat Notebooks

#81

Post by SkyMarshal »

visarga wrote: post #53
SkyMarshal wrote: post #30

Earlier quoted context omitted.

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…

Not even humans with PhD can do physics research without a lab. How could a model with just a few tokens of context window and no body do that?

Obviously I’m talking about mathematical/computational physics, not experimental physics. I don’t expect the AI to build itself a tokamak to run experiments on.

Re: Chat Notebooks

#82

Post by cshimmin »

theodoregray wrote: post #76
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…

It's a fair claim if you make it for Wolfram Research rather than Stephen Wolfram personally (which is all he ever does). Jupyter notebooks were inspired by Mathematica notebooks: that's widely known and has been explicitly said in blog posts and elsewhere by the creators of Jupyter. It's no secret… And as the designer and developer of Mathematica notebooks I am flattered and honored that my ideas are now so widely u…

Amazing, thank you for taking the time to share this! Big fan of notebooks in general and of Mathematica in particular.

Re: Chat Notebooks

#83

Post by lurker137 »

connordg wrote: post #74
lurker137 wrote: post #46

Earlier quoted context omitted.

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

There isn't a screenshot of this in Stephen's blog, but he does mention[1] the ability to evaluate a single 'ChatInput' multiple times, which preserves all previous evaluations and allows you to tab through them to pick the best one. (You can see a screenshot of what the arrow tab switcher looks like on the left side of this[2] example in the Chatbook README.md). One of the nice advantages of a notebook interface to…

That's fantastic, it seems like such an essential feature that should have been part of the regular OpenAi UI on launch

Re: Chat Notebooks

#84

Post by pedrosorio »

simsla wrote: post #72
donpark wrote: post #10

Earlier quoted context omitted.

Having been there when it was first announced, I think his "claim" has substance. Mathematica clearly defined the "notebooks" UI as it is known today.

It's not about him being right or not, but about it being irrelevant.

In a blog post about integrating LLMs into the notebook paradigm, going back to the invention of notebooks by the same company is irrelevant?

Re: Chat Notebooks

#86

Post by B1FF_PSUVM »

theodoregray wrote: post #76
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…

It's a fair claim if you make it for Wolfram Research rather than Stephen Wolfram personally (which is all he ever does). Jupyter notebooks were inspired by Mathematica notebooks: that's widely known and has been explicitly said in blog posts and elsewhere by the creators of Jupyter. It's no secret… And as the designer and developer of Mathematica notebooks I am flattered and honored that my ideas are now so widely u…

(Got curious if it was officially credited, found it was)

Item #8 at https://www.wolfram.com/mathematica/scrapbook/

""""

1987: The Mathematica front end begins to take shape…

[screenshots]

(Theo Gray invents cells and groups… and other things still seen today…)

"""

Re: Chat Notebooks

#87

Post by B1FF_PSUVM »

hliyan wrote: post #39
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!

I believe PowerPoint simply buried many better ways of presenting bytesized information chunks to the world. It prioritized the author's laziness over audience comprehension.

> prioritized the author's laziness over audience comprehension.

Is that even possible?

The audience - people in general - are very resistant to having knowledge/ideas shoved into their brains, and I don't blame them, 90% of it is crap.

Authors have to work very hard to overcome this. "Tell them what you're going to tell them, tell them, tell them what you told them", best advice I got on presentations.

If there was anything better the Powerpoint, short of "killing the unbelievers", it would probably have made a mint by now.

Post reply on HN