Future of Knowledge Connecting Language and Computation

Machine Learning Street Talk

https://youtu.be/z5WZhCBRDpU

132,828 views  Mar 23, 2023  Episode #110

CHATGPT+WOLFRAM! You saw it HERE first!

ChatGPT + Wolfram: The Future of AI is Here!

Pod version: https://podcasters.spotify.com/pod/sh...

Support us! https://www.patreon.com/mlst 

MLST Discord: https://discord.gg/aNPkGUQtc5

Stephen's announcement post: https://writings.stephenwolfram.com/2... 

OpenAI's announcement post: https://openai.com/blog/chatgpt-plugins 

In an era of technology and innovation, few individuals have left as indelible a mark on the fabric of modern science as our esteemed guest, Dr. Steven Wolfram. 

Dr. Wolfram is a renowned polymath who has made significant contributions to the fields of physics, computer science, and mathematics. A prodigious young man too, Wolfram earned a Ph.D. in theoretical physics from the California Institute of Technology by the age of 20. He became the youngest recipient of the prestigious MacArthur Fellowship at the age of 21.

Wolfram's groundbreaking computational tool, Mathematica, was launched in 1988 and has become a cornerstone for researchers and innovators worldwide. In 2002, he published "A New Kind of Science," a paradigm-shifting work that explores the foundations of science through the lens of computational systems.

In 2009, Wolfram created Wolfram Alpha, a computational knowledge engine utilized by millions of users worldwide. His current focus is on the Wolfram Language, a powerful programming language designed to democratize access to cutting-edge technology.

Wolfram's numerous accolades include honorary doctorates and fellowships from prestigious institutions. As an influential thinker, Dr. Wolfram has dedicated his life to unraveling the mysteries of the universe and making computation accessible to all.

First of all... we have an announcement to make, you heard it FIRST here on MLST! ....

[00:00] Intro

[02:57] Big announcement! Wolfram + ChatGPT!

[05:33] What does it mean to understand?

[13:48] Feeding information back into the model

[20:09] Semantics and cognitive categories

[23:50] Navigating the ruliad

[31:39] Computational irreducibility

[38:43] Conceivability and interestingness

[43:43] Human intelligible sciences

Wolfram can Plug into GPT for new SuperPowers

Saw this hinted at a while back. Wolfram Alpha has had unique analytic capabilities for some time, now you can link these to ChatGPT.  Via a plugin.   Apparently there is the ability to add other plugins as well. Thinking about some possibilities.   How to hinted at blow, note current restrictions with OpenAI updates.   Good intro to wolfram capabilities,  which were used by some in out enterprise,  most for component testing analytics.    Wolfram also gives you the bonus of some good integrated analytics visualization. The article below contains some very interesting examples.  And in addition describes how the neural nets of large language models relate to the Neural nets that Wolfram has been talking about for years relate.   All this is quite exciting,  but you may have to wait until Plugins are available in ChatGPT. 

ChatGPT Gets Its “Wolfram Superpowers”!

March 23, 2023

To enable the functionality described here, select and install the Wolfram plugin from within ChatGPT.

Note that this capability is so far available only to some ChatGPT Plus users; for more information, see OpenAI’s announcement.

In Just Two and a Half Months…

Early in January I wrote about the possibility of connecting ChatGPT to Wolfram|Alpha. And today—just two and a half months later—I’m excited to announce that it’s happened! Thanks to some heroic software engineering by our team and by OpenAI, ChatGPT can now call on Wolfram|Alpha—and Wolfram Language as well—to give it what we might think of as “computational superpowers”. It’s still very early days for all of this, but it’s already very impressive—and one can begin to see how amazingly powerful (and perhaps even revolutionary) what we can call “ChatGPT + Wolfram” can be.

Back in January, I made the point that, as an LLM neural net, ChatGPT—for all its remarkable prowess in textually generating material “like” what it’s read from the web, etc.—can’t itself be expected to do actual nontrivial computations, or to systematically produce correct (rather than just “looks roughly right”) data, etc. But when it’s connected to the Wolfram plugin it can do these things. So here’s my (very simple) first example from January, but now done by ChatGPT with “Wolfram superpowers” installed:

How far is it from Tokyo to Chicago?

It’s a correct result (which in January it wasn’t)—found by actual computation. And here’s a bonus: immediate visualization:

Show the path

How did this work? Under the hood, ChatGPT is formulating a query for Wolfram|Alpha—then sending it to Wolfram|Alpha for computation, and then “deciding what to say” based on reading the results it got back. You can see this back and forth by clicking the “Used Wolfram” box (and by looking at this you can check that ChatGPT didn’t “make anything up”):  .... '

Wolfram Alpha Introduces Math Input

From Wolfram

We are excited to talk about a feature we released this summer that we call Math Input. We’ve had many requests to add this feature to the site, and after a lot of hard work from multiple teams, we’re ready to share it with you. Head over to Wolfram|Alpha to see it for yourself:

(Many, many examples at the link.   For those needing math support for analytical exercises and specific quant results.    We tested Wolfram Alpha in the enterprise)

Siri and Wolfram Alpha

I had to use Siri recently, and was reminded that she is also connected to the Wolfram Alpha Knowledge base.  Here are some general examples of that.   Works well in particular for science constants and algorithms.    Need to keep that in mind. ....' 

Wolfram Alpha Notebook Turns One: Does Chemistry

This remains taking a close look at.   We explored WolframAlpha itself.  What I liked here was its use in specific context, like here: Chemistry.  Does this help or diminish teaching in the basics of analytical chemistry?  Note the inclusion of 'inferences' in your queries,  how should they be validated?

Peter Falloon, Jeremy Stratton-Smith:The Wolfram Alpha Chemistry Team
Wolfram|Alpha Notebook Edition Turns One: Now with Support for Chemistry, Demonstrations and 
Brad Janes, Wolfram|Alpha Math Content Manager
Peter Falloon, Data & Semantics Engineering
Jeremy Stratton-Smith, Math Developer, Wolfram|Alpha Math Content

The WolframAlpha Chemistry Team
Wolfram|Alpha Notebook Edition was released nearly a year ago, and we’re proud to share what the team has been working on since. In addition to the improvements made to Wolfram|Alpha itself, new input and output suggestions were added. There were parsing fixes, additions to the Wolfram|Alpha-to-Wolfram Language translation and some of the normal improvements one would expect. There are also some bigger features and interesting new capabilities that we will explore in a bit more detail here.

If you haven’t checked out Wolfram|Alpha Notebook Edition in a while, we’d like to invite you to revisit. With education looking a little different for many people right now, this could be a great time to explore this exciting new way to interface with Wolfram technologies.

One of the most useful features of any notebook-based computational environment is the ability to reuse the result of a prior calculation as the input to a new one. Using this, computations can be built up using an intuitive “step-by-step” approach and the need for cutting/pasting or retyping is reduced. 

In Wolfram|Alpha Notebook Edition, previous outputs can be referenced in a variety of ways, ranging from familiar Wolfram Language constructs such as %n or Out[n] to natural language expressions such as “simplify the last result,” “plot the above” or “square it.” In certain cases, an explicit reference needn’t even appear: e.g. if you input “y = sin(x^3)” followed by “make a plot,” Wolfram|Alpha Notebook Edition will infer that you want to make a plot of the previous equation. 

This functionality, which has been under continuous development since the release of this product, has recently been extended to leverage the powerful semantic capabilities that power the Suggestions Bar. This allows for context-dependent tailoring of results containing references to previous outputs based on the semantic types of those results. As we build out this functionality, you can expect to see Wolfram|Alpha Notebook Edition becoming even smarter in helping you to build up your computations.   .... "

Wolfram Alpha: Notebook Edition

Been a while since I used this in the enterprise, but here is a new release of interest.  I would heartily recommend this as a teaching environment for math for any engaged student who is using a computer.

The Ease of Wolfram|Alpha, the Power of Mathematica: Introducing Wolfram|Alpha Notebook Edition    ....   Wolfram|Alpha Notebook Edition

The Next Big Step for Wolfram|Alpha

Wolfram|Alpha has been a huge hit with students. Whether in college or high school, Wolfram|Alpha has become a ubiquitous way for students to get answers. But it’s a one-shot process: a student enters the question they want to ask (say in math) and Wolfram|Alpha gives them the (usually richly contextualized) answer. It’s incredibly useful—especially when coupled with its step-by-step solution capabilities.

But what if one doesn’t want just a one-shot answer? What if one wants to build up (or work through) a whole computation? Well, that’s what we created Mathematica and its whole notebook interface to do. And for more than 30 years that’s how countless inventions and discoveries have been made around the world. It’s also how generations of higher-level students have been taught.

But what about students who aren’t ready to use Mathematica yet? What if we could take the power of Mathematica (and what’s now the Wolfram Language), but combine it with the ease of Wolfram|Alpha?

Well, that’s what we’ve done in Wolfram|Alpha Notebook Edition.

It’s built on a huge tower of technology, but what it does is to let any student—without learning any syntax or reading any documentation—immediately build up or work through computations. Just type input the way you would in Wolfram|Alpha. But now you’re not just getting a one-shot answer. Instead, everything is in a Wolfram Notebook, where you can save and use previous results, and build up or work through a whole computation:   .... "