Instant Plugins for ChatGPT: Introducing the Wolfram ChatGPT Plugin Kit

Very useful piece, with how to set this up linking to computational resources.  Technical.  

Instant Plugins for ChatGPT: Introducing the Wolfram ChatGPT Plugin Kit     April 27, 2023

This is the first in a series of posts about new LLM-related technology associated with the Wolfram technology stack.

Build a New Plugin in under a Minute…

A few weeks ago, in collaboration with OpenAI, we released the Wolfram plugin for ChatGPT, which lets ChatGPT use Wolfram Language and Wolfram|Alpha as tools, automatically called from within ChatGPT. One can think of this as adding broad “computational superpowers” to ChatGPT, giving access to all the general computational capabilities and computational knowledge in Wolfram Language and Wolfram|Alpha.

But what if you want to make your own special plugin, that does specific computations, or has access to data or services that are for example available only on your own computer or computer system? Well, today we’re releasing a first version of a kit for doing that. And building on our whole Wolfram Language tech stack, we’ve managed to make the whole process extremely easy—to the point where it’s now realistic to deploy at least a basic custom ChatGPT plugin in under a minute.

There’s some (very straightforward) one-time setup you need—authenticating with OpenAI, and installing the Plugin Kit. But then you’re off and running, and ready to create your first plugin. ... ' 

Machine Learning Street talk: Wolfram Announcement

I mentioned the below announcement of being able to plug in WolframAlpha capabilities in ChatGPT.  I found the the talk here to be insightful about how language models could interact with computational models.  And how can this be used yet further improve AI.  Technical, but could be pointing us to yet more wonderful things.

Machine Learning Street Talk    https://youtu.be/z5WZhCBRDpU

132,828 views  Mar 23, 2023  #110  Episode #110

HUGE ANNOUNCEMENT, 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

What Is ChatGPT Doing... and Why Does It Work?

Good piece by Stephen Wolfram,  below the intro: 

What Is ChatGPT Doing... and Why Does It Work?

It’s Just Adding One Word at a Time

That ChatGPT can automatically generate something that reads even superficially like human-written text is remarkable, and unexpected. But how does it do it? And why does it work? My purpose here is to give a rough outline of what’s going on inside ChatGPT—and then to explore why it is that it can do so well in producing what we might consider to be meaningful text. I should say at the outset that I’m going to focus on the big picture of what’s going on—and while I’ll mention some engineering details, I won’t get deeply into them. (And the essence of what I’ll say applies just as well to other current “large language models” [LLMs] as to ChatGPT.)

The first thing to explain is that what ChatGPT is always fundamentally trying to do is to produce a “reasonable continuation” of whatever text it’s got so far, where by “reasonable” we mean “what one might expect someone to write after seeing what people have written on billions of webpages, etc.”

So let’s say we’ve got the text “The best thing about AI is its ability to”. Imagine scanning billions of pages of human-written text (say on the web and in digitized books) and finding all instances of this text—then seeing what word comes next what fraction of the time. ChatGPT effectively does something like this, except that (as I’ll explain) it doesn’t look at literal text; it looks for things that in a certain sense “match in meaning”. But the end result is that it produces a ranked list of words that might follow, together with “probabilities”:

And the remarkable thing is that when ChatGPT does something like write an essay what it’s essentially doing is just asking over and over again “given the text so far, what should the next word be?”—and each time adding a word. (More precisely, as I’ll explain, it’s adding a “token”, which could be just a part of a word, which is why it can sometimes “make up new words”.) ... '

Trees in Wolfram

 I see that the Wolfram language has added new and improved features using Trees.  Below a good intro.  As usual, Their capabilities,  which we used in house, are nicely done and described, worth a look. 

New in 13: Trees

April 22, 2022, Stephen Wolfram

Two years ago we released Version 12.0 of the Wolfram Language. Here are the updates in trees since then, including the latest features in 13.0. The contents of this post are compiled from Stephen Wolfram’s Release Announcements for 12.1, 12.2, 12.3 and 13.0.

Trees! (May 2021)

Based on the number of new built-in functions the clear winner for the largest new framework in Version 12.3 is the one for trees. We’ve been able to handle trees as a special case of graphs for more than a decade (and of course all symbolic expressions in the Wolfram Language are ultimately represented as trees). But in Version 12.3 we’re introducing trees as first-class objects in the system.

The fundamental object is Tree:  ....(much more at the link] 

Microsoft Partners with Wolfram for Data

Just noted this, a good direction.  Can see this as useful, especially in filling analyses with meta or test data.  Which we often integrated.    I just also started to use Wolfram Alpha data as part of the Siri assistant.

Wolfram Data Intelligence:    from Wolfram.com

New in Microsoft

Microsoft has partnered with Wolfram to intelligently add meaning to your data. Identify and auto-fill thousands of data points from hundreds of data types directly in Microsoft Excel. Expertly curated data provides instant interactivity and immediate answers.

100+ Integrated Data Types Available

(Click a data type to find out more)  ..... 

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)

Sleuthing Crypto Ransom Payments?

Found this most interesting.   Very  technical look at the approach. Includes all the Wolfram code. reviewing now.  Could this be further developed?  Makes me think about the overall problem.   Contact Wolfram for more information.

DarkSide Update: The FBI Hacks the Hackers?

June 9, 2021

By Dariia Porechna, Cryptography and Blockchain, Wolfram Language Development

In my May 25, 2021, blog post “Sleuthing DarkSide Crypto-Ransom Payments with the Wolfram Language,”   I detailed how I used the Wolfram Language, public knowledge and some guesswork to track crypto-ransom payments made by Colonial Pipeline on May 8 and Brenntag on May 11 to the Russian hacker group DarkSide. These payments, which totaled millions of dollars, were subsequently distributed to different accounts, and on May 13, DarkSide announced it was disbanding.

But the story didn’t end when DarkSide announced its dissolution.

On June 7, the FBI seized 63.7 bitcoin (BTC), approximately $2.3 million USD, from one of the addresses to which DarkSide’s cluster, described in my earlier post, sent their ransom funds. Normally, this should have been inaccessible to anyone without a private key for that address. The FBI apparently managed, however, to obtain one.

Did the FBI run a brute-force attack on a billion-dollar supercomputer to find the private key? For the elliptic curve secp256k1, which Bitcoin is based on, the number of possible private keys for a particular public key is approximately:  .... " 

Wolfram Physics: One Year Update: How’s It Going?

With a physics background, always found this somewhat ungraspable, but on it goes.  And now an update.   I have yet to hear that traditional physics is applauding this, so I guess that is still my main objection.   And I don't have the time to do my own fundamental research.   So here it is:

Wolfram Physics:  On Year Update:  How’s It Going?

When we launched the Wolfram Physics Project a year ago today, I was fairly certain that—to my great surprise—we’d finally found a path to a truly fundamental theory of physics, and it was beautiful. A year later it’s looking even better. We’ve been steadily understanding more and more about the structure and implications of our models—and they continue to fit beautifully with what we already know about physics, particularly connecting with some of the most elegant existing approaches, strengthening and extending them, and involving the communities that have developed them.

And if fundamental physics wasn’t enough, it’s also become clear that our models and formalism can be applied even beyond physics—suggesting major new approaches to several other fields, as well as allowing ideas and intuition from those fields to be brought to bear on understanding physics.

Needless to say, there is much hard work still to be done. But a year into the process I’m completely certain that we’re “climbing the right mountain”. And the view from where we are so far is already quite spectacular.

We’re still mostly at the stage of exploring the very rich structure of our models and their connections to existing theoretical frameworks. But we’re on a path to being able to make direct experimental predictions, even if it’ll be challenging to find ones accessible to present-day experiments. But quite independent of this, what we’ve done right now is already practical and useful—providing new streamlined methods for computing several important existing kinds of physics results.

The way I see what we’ve achieved so far is that it seems as if we’ve successfully found a structure for the “machine code” of the universe—the lowest-level processes from which all the richness of physics and everything else emerges. It certainly wasn’t obvious that any such “machine code” would exist. But I think we can now be confident that it does, and that in a sense our universe is fundamentally computational all the way down. But even though the foundations are different, the remarkable thing is that what emerges aligns with important mathematical structures we already know, enhancing and generalizing them.

From four decades of exploring the computational universe of possible programs, my most fundamental takeaway has been that even simple programs can produce immensely complex behavior, and that this behavior is usually computationally irreducible, in the sense that it can’t be predicted by anything much less than just running the explicit computation that produced it. And at the level of the machine code our models very much suggest that our universe will be full of such computational irreducibility.

Tezos and Wolfram for Blockchain

 New to me, and interesting, with quite a bit of detail and even sample code.  Will be examining smart contract implications.

Third-Generation Blockchain Functionality with Tezos and the Wolfram Language

As CEO of Wolfram Blockchain Labs (WBL), (John Woodard, CEO Wolfram Blockchain Labs)   I think one of the most exciting parts of my job is collaborating with other leaders in the blockchain space to expand tools for developers and business use cases. For several years now, we’ve been adding a steady stream of blockchain functionality into the Wolfram Language to enable development of knowledge-based distributed applications and computational contracts. You may have noticed the growing number of popular blockchains (ARK, Bitcoin, bloxberg, Cardano, Ethereum, MultiChain…) partnering with us and integrating into our platform. It’s already led to some cool explorations, and we have a lot more in the pipeline.

Today, WBL is happy to announce its latest such collaboration, a partnership with TQ Tezos. That includes Tezos blockchain integration in the Wolfram Language, which is great news for smart contract developers and enthusiasts. But that’s just the beginning. Our long-term plans include a lot of big ideas that we think everyone will be excited about!   ... " 

Wolfram and Ethereum

Saw this late, but interesting.

Investigating the Ethereum Gold-Bug and Blockchain in the Wolfram Language

Wolfram Blog by Christian Pasquel 

Blockchain was integrated into the Wolfram Language in 2018 with the release of Version 11.3, featuring a set of functions that is constantly improved and expanded upon by our team. Currently supporting a seamless connection to the Bitcoin, Ethereum, ARK and bloxberg mainnets, testnets and devnets, Wolfram introduced to the distributed ledger technology (DLT) space its philosophy of injecting computational intelligence everywhere through Wolfram Blockchain Labs, with the mission of enabling blockchain-based commerce and business model innovation.  ... 

Feynman's Advice to a Young Stephen Wolfram

Particularly interesting if you are intrigued by the origin and transmission of ideas.   As I am.  This blog for example was established to continue communications to our innovation center visitors over the years.   It has morphed to a more technical emergent technology alerting method.  And when it can it connects with rising memes, and aims to create value from them.

Richard Feynman’s Advice to a Young Stephen Wolfram (1985)
Jørgen Veisdal  in Medium.  .... 

New Physics: All the Way Down?

Descriptive.  But will it show us something really predictively new?

THE THIRD CULTURE
Computation All the Way Down In the Edge
A Conversation with Stephen Wolfram

We're now in this situation where people just assume that science can compute everything, that if we have all the right input data and we have the right models, science will figure it out. If we learn that our universe is fundamentally computational, that throws us right into the idea that computation is a paradigm you have to care about. The big transition was from using equations to describe how everything works to using programs and computation to describe how things work. And that's a transition that has happened after 300 years of equations. The transition time to using programs has been remarkably quick, a decade or two. One area that was a holdout, despite the transition of many fields of science into the computational models direction, was fundamental physics.

If we can firmly establish this fundamental theory of physics, we know it's computation all the way down. Once we know it's computation all the way down, we're forced to think about it computationally. One of the consequences of thinking about things computationally is this phenomenon of computational irreducibility. You can't get around it. That means we have always had the point of view that science will eventually figure out everything, but computational irreducibility says that can't work. It says that even if we know the rules for the system, it may be the case that we can't work out what that system will do any more efficiently than basically just running the system and seeing what happens, just doing the experiment so to speak. We can't have a predictive theoretical science of what's going to happen.

STEPHEN WOLFRAM is a scientist, inventor, and the founder and CEO of Wolfram Research. He is the creator of the symbolic computation program Mathematica and its programming language, Wolfram Language, as well as the knowledge engine Wolfram|Alpha. His most recent endeavor is The Wolfram Physics Project. He is also the author, most recently, of A Project to Find the Fundamental Theory of Physics. ...."  More.

Wolfram Needs Help Modeling Universe

Just mentioned related work:

Wolfram, Modeling Our Universe, Needs Your Help
Popular Mechanics
By Courtney Linder

Physicist Stephen Wolfram has launched the Wolfram Physics Project to crowdsource research to model the universe's fundamental physical laws. The project incorporates “the most important works in physics,” including 800 pages of documents Wolfram authored, and 430 hours of video documenting brainstorming sessions between Wolfram and his colleagues. Wolfram and project participants will use computational models to simulate possible universes. The project webpage lists a Registry of Notable Universes compiling about 1,000 rules for the project. Said Wolfram, “I hope soon there might just be a rule entered in the Registry that has all the right properties, and that we’ll slowly discover that, yes, this is it—our universe finally decoded." .... '

Physics as Automata

Fascinating read.    And as a person with background in physics and computer science I find this fascinating.   Have read parts of Wolfram's 'big' book, which initially posed aspects of this solution.  Admit to being somewhat mysttified by the solution and what to do with it.   Technical, the article is a good start.

Finally We May Have a Path to the Fundamental Theory of Physics…
and It’s Beautiful

Website: Wolfram Physics Project

Technical Intro: A Class of Models with the Potential to Represent Fundamental Physics
How We Got Here: The Backstory of the Wolfram Physics Project
Visual summary of the Wolfram Physics Project

I Never Expected This
It’s unexpected, surprising—and for me incredibly exciting. To be fair, at some level I’ve been working towards this for nearly 50 years. But it’s just in the last few months that it’s finally come together. And it’s much more wonderful, and beautiful, than I’d ever imagined.

In many ways it’s the ultimate question in natural science: How does our universe work? Is there a fundamental theory? An incredible amount has been figured out about physics over the past few hundred years. But even with everything that’s been done—and it’s very impressive—we still, after all this time, don’t have a truly fundamental theory of physics.

Back when I used do theoretical physics for a living, I must admit I didn’t think much about trying to find a fundamental theory; I was more concerned about what we could figure out based on the theories we had. And somehow I think I imagined that if there was a fundamental theory, it would inevitably be very complicated.

But in the early 1980s, when I started studying the computational universe of simple programs I made what was for me a very surprising and important discovery: that even when the underlying rules for a system are extremely simple, the behavior of the system as a whole can be essentially arbitrarily rich and complex.

And this got me thinking: Could the universe work this way? Could it in fact be that underneath all of this richness and complexity we see in physics there are just simple rules? I soon realized that if that was going to be the case, we’d in effect have to go underneath space and time and basically everything we know. Our rules would have to operate at some lower level, and all of physics would just have to emerge. ...."

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:   .... "

Wolfram: Mining the Computational Universe

Intriguing half hour talk.  A response to the broad entry of AI,  or a claim to a new architecture of computation?    Just recently reexamined here the anniversary of Wolfram Alpha.

In the Edge:
Mining the Computational Universe
A Talk By Stephen Wolfram

I've spent several decades creating a computational language that aims to give a precise symbolic representation for computational thinking, suitable for use by both humans and machines. I'm interested in figuring out what can happen when a substantial fraction of humans can communicate in computational language as well as human language. It's clear that the introduction of both human spoken language and human written language had important effects on the development of civilization. What will now happen (for both humans and AI) when computational language spreads?

STEPHEN WOLFRAM is a scientist, inventor, and the founder and CEO of Wolfram Research. He is the creator of the symbolic computation program Mathematica and its programming language, Wolfram Language, as well as the knowledge engine Wolfram|Alpha. He is also the author of A New Kind of Science. 

Mining the Computational Universe

STEPHEN WOLFRAM: I thought I would talk about my current thinking about computation and our interaction with it. The first question is, how common is computation? People have the general view that to make something do computation requires a lot of effort, and you have to build microprocessors and things like this. One of the things that I discovered a long time ago is that it’s very easy to get sophisticated computation.

I’ve studied cellular automata, studied Turing machines and other kinds of things—as soon as you have a system whose behavior is not obviously simple, you end up getting something that is as sophisticated computationally as it can be. This is something that is not an obvious fact. I call it the principle of computational equivalence. At some level, it’s a thing for which one can get progressive evidence. You just start looking at very simple systems, whether they’re cellular automata or Turing machines, and you say, "Does the system do sophisticated computation or not?" The surprising discovery is that as soon as what it’s doing is not something that you can obviously decode, then one can see, in particular cases at least, that it is capable of doing as sophisticated computation as anything. For example, it means it’s a universal computer.  .... " 

Wolfram Alpha is 10!

I was an early tester, loved it.   An assistant that emphasized the computable!  Free and amazing.  How great to see things as computable.   But somehow I drifted off to others.   You know the other glitzy assistants, often mentioned here.     And those I can ask computable things like:  how many ounces in a deciliter?... but that's not very fun or meaningful.

I saw WA as a semantic DB that could be made to answer questions like:  Calculate X using Y in region Z while also showing me the risk profile.  With our data and public data.  With the usual metadata.   Systematic data we use all the time.   But it was harder to set it up to do that kind of thing than I thought,  nobody bought.

 I was careful to include Wolfram/Alpha in my known assistant list, but rarely visited.  Few had head of it.   But now this considerable article about where Wolfram/Alpha is today and where it may be going.  But Have not read it yet, but about to.  I am back, WA are you listening, want to talk?

You can try Wolfram/Alpha here.

The Wolfram|Alpha Story  From the WolframBlog.

Today it’s 10 years since we launched Wolfram|Alpha. At some level, Wolfram|Alpha is a never-ending project. But it’s had a great first 10 years. It was a unique and surprising achievement when it first arrived, and over its first decade it’s become ever stronger and more unique. It’s found its way into more and more of the fabric of the computational world, both realizing some of the long-term aspirations of artificial intelligence, and defining new directions for what one can expect to be possible. Oh, and by now, a significant fraction of a billion people have used it. And we’ve been able to keep it private and independent, and its main website has stayed free and without external advertising.

For me personally, the vision that became Wolfram|Alpha has a very long history. I first imagined creating something like it more than 47 years ago, when I was about 12 years old. Over the years, I built some powerful tools—most importantly the core of what’s now Wolfram Language. But it was only after some discoveries I made in basic science in the 1990s that I felt emboldened to actually try building what’s now Wolfram|Alpha.

It was—and still is—a daunting project. To take all areas of systematic knowledge and make them computable. To make it so that any question that can in principle be answered from knowledge accumulated by our civilization can actually be answered, immediately and automatically. .... "

Mathematica Expands

Been a long time since I worked with Wolfram's Mathematica.  Was always impressed with what the package provided.  Especially useful for people that already have a math background.    Also good to let people/students with a strong interest in Math expand their mathematical powers.

They are coming up with a considerable update I have started to scan.  Lots of new descriptive documentation that looks good.  Now includes examples about how to do DeepLearning and blockchains with Mathematica.  The article below has a long description of the capabilities.

Version 12 Launches Today! (And It’s a Big Jump for Wolfram Language and Mathematica)
April 16, 2019 — By Stephen Wolfram  ... '

Orchard Planting

Also popped up, the 'Orchard Planting Problem',  new to me.   This Wolfram article looks at it in great depth, combinatorially and visually ....  Perhaps this would have been of more interest when we managed softwood forests.  Also a good example of what can be done with Wolfram tools.

Cultivating New Solutions for the Orchard-Planting Problem 
Ed Pegg Jr, Editor, Wolfram Demonstrations Project ... "

Computational Essays and Dialogs

This was intriguing. Could it also be used to state how AI algorithms are created,  to make them transparent to their users?   Also how related issues like process, risk and rewards are included in the 'conversation'.   In the below example Wolfram states the example in the Wolfram Language, but it could be done in any code representation.    And taking it beyond an essay, this could also be called a 'computational dialog', to include other influencing players, like the business process owner and other parties involved.   Even competitors that react to a public process.

A Powerful Way to Express Ideas by Stephen Wolfram

People are used to producing prose—and sometimes pictures—to express themselves. But in the modern age of computation, something new has become possible that I’d like to call the computational essay.

I’ve been working on building the technology to support computational essays for several decades, but it’s only very recently that I’ve realized just how central computational essays can be to both the way people learn, and the way they communicate facts and ideas. Professionals of the future will routinely deliver results and reports as computational essays. Educators will routinely explain concepts using computational essays. Students will routinely produce computational essays as homework for their classes.  .... "