Wolfram Alpha With ChatGPT Looks Like A Killer Combo

Ever looked at Wolfram Alpha and the development of Wolfram Language and thought that perhaps Stephen Wolfram was a bit ahead of his time? Well, maybe the times have finally caught up because Wolfram plus ChatGPT looks like an amazing combo. That link goes to a long blog post from Stephen Wolfram that showcases exactly how and why the two make such a wonderful match, with loads of examples. (If you’d prefer a video discussion, one is embedded below the page break.)

OpenAI’s ChatGPT is a large language model (LLM) neural network, or more conventionally, an AI system capable of conversing in natural language. Thanks to a recently announced plugin system, ChatGPT can now interact with remote APIs and therefore use external resources.

ChatGPT’s natural language processing ability enables some pretty impressive interactions with Wolfram, enabling the kind of exchange you see here (click to enlarge.)

This is meaningful because LLMs are very good at processing natural language and generating plausible-sounding output, but whether or not the output is factually correct can be another matter. It’s not so much that ChatGPT is especially prone to confabulation, it’s more that the nature of an LLM neural network makes it difficult to ask “why exactly did you come up with your answer, and not something else?” In addition, asking ChatGPT to do things like perform nontrivial calculations is a bit of a square peg and round hole situation.

So how does the Wolfram plugin change that? When asked to produce data or perform computations, ChatGPT can now hand it off to Wolfram Alpha instead of attempting to generate the answer by itself.  Both sides use their strengths in this arrangement. First, ChatGPT interprets the user’s question and formulates it as a query, which is then sent to Wolfram Alpha for computation, and ChatGPT structures its response based on what it got back. In short, ChatGPT can now ask for help to get data or perform a computation, and it can show the receipts when it does.

Continue reading “Wolfram Alpha With ChatGPT Looks Like A Killer Combo”

Wolfram Alpha Electronic Tips

Electronics takes a lot of math. Once you’ve mastered all the algebra and calculus, though, it is sometimes a drag to go through the motions. It also can be error-prone. But these days, you have Wolfram Alpha which will do all the work for you and very easily. I use it all the time when I’m too lazy to solve an equation or do an integral by hand. But did you know it actually has some features specifically for electronics?

If you want to do a lot with electronics — or nearly any technical field — you are going to have to learn some math and you shouldn’t just rely on tools like Wolfram to skirt understanding the math. Unfortunately, schools often teach us that the point to math is to get a correct answer. For bookkeepers and at the very final stage of engineering, that may be true. But the real value to math for engineers and scientists is to develop intuition about things. If you increase a capacitor’s value does that make its reactance go up or down? Does a little change in load resistance make a corresponding small change in power consumption or is it a lot more? So you should understand why math works. But once you do, using a tool like Wolfram can free you to focus on the abstract questions instead of the detailed “grunt work.”

 

Tip #1: Split Personality

Wolfram can’t seem to decide if it is a symbolic math program or a search engine. Sometimes just putting a topic name in can lead to some interesting calculations. For example, look what happens when you enter the word opamp: Continue reading “Wolfram Alpha Electronic Tips”

Wolfram Alpha Shows Its Work

The bane of math students everywhere is the teacher asking for you to show your work. If you’ve grown up where a computer is a normal part of school work, that might annoy you since a lot of tools just give you an answer. We aren’t suggesting you cheat at homework, but we did notice that Wolfram Alpha now shows more of its work when it solves many common math problems.

Granted, the site has always shown work on some problems. However, a recent update shows more intermediate steps and also covers more kinds of problems in a step-by-step format. There are examples, but be aware that for general use, you do need to upgrade to pro (about $6 a month or less if you are student or teacher).

Continue reading “Wolfram Alpha Shows Its Work”

Forget Siri – Make Wolfram Alpha Your Personal Assistant

So you can spend a bundle on a new phone and it comes with a voice-activated digital assistant. But let’s be honest, it’s much more satisfying if you coded up this feature yourself. Here’s a guide on doing just that by combining an Asterisk server with the Wolfram Alpha API.

Asterisk is a package we are already familiar with. It’s an open source Private Branch Exchange suite that lets you build your own telephone network. Chances are, you’re not going to build one just for this project, but if you do make sure to document the process and let us know about it. With the Asterisk server in place you just need to give the assistant script an extension (in this case it’s 4747).

But then there’s the problem of translating your speech into text which can be submitted as a Wolfram query. There’s an API for that too which uses Google to do that translation. From there you can tweak abbreviations and other parameters, but all-in-all your new assistant is ready to go. Call it up and ask what to do when you have a flat tire (yeah, that commercial drives us crazy too).

[Thanks M]