/* ---- Google Analytics Code Below */

Friday, March 24, 2023

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”):  .... '

No comments: