Since ChatGPT uses randomness in generating its responses, different things can happen even when you ask it the exact same question (even in a fresh session). If you actually try these examples, don’t be surprised if they work differently (sometimes better, sometimes worse) from what I’m showing here. And, as a bonus, we can also make a visualization:Īnother example from back in January that now comes out correctly is: In January, I noted that ChatGPT ended up just “making up” plausible (but wrong) data when given this prompt:īut now it calls the Wolfram plugin and gets a good, authoritative answer. Let’s try another example, also from what I wrote in January:Ī fine result, worthy of our technology. But the upshot is a good, correct result, knitted into a nice, flowing piece of text.
There are lots of nontrivial things going on here, on both the ChatGPT and Wolfram|Alpha sides. 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”): 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. And here’s a bonus: immediate visualization:
It’s a correct result (which in January it wasn’t)-found by actual computation. So here’s my (very simple) first example from January, but now done by ChatGPT with “Wolfram superpowers” installed: But when it’s connected to the Wolfram plugin it can do these things. 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.īack 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. 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”. In Just Two and a Half Months…Įarly in January I wrote about the possibility of connecting ChatGPT to Wolfram|Alpha. Note that this capability is so far available only to some ChatGPT Plus users for more information, see OpenAI’s announcement. To enable the functionality described here, select and install the Wolfram plugin from within ChatGPT.
0 kommentar(er)
