ChatGPT can now call Wolfram Alpha
This is a match made in heaven, which makes ChatGPT actually useful for factual data. Or the inverse, it makes Wolfram Alpha even more accessible.
That example screenshot of ChatGPT generating three queries to Wolfram Alpha in succession in order to answer the initial question is amazing. It's just how a human might have used Wolfram Alpha to do the same.
Wolfram Alpha was my ChatGPT when I was in school. And many of the same issues ("how will kids learn math now?") were raised at the time.
...Yeah, this seems like a great match, no complaints from me. Those kinds of responses are exactly what LLMs need.
OpenAI and Microsoft have been killing it not only in product but in the go-to-market work they've been doing long before launch. Really superb work.
With seemingly every launch, they have a slate of really compelling launch partners already using the new service, giving them a big press bump (from the articles those partners write) and social proof, and of course the product is better because it's already been tested with real customers.
Masterclass in product management.
This seems very significant to me. Wolfram's biggest problem was always being too geeky and finnicky and pain-in-the-ass-y for most people to use. But ChatGPT is a perfect translator for it. This could be very cool.
I bet the Zapier integration is going to be an alignment/security dumpster-fire.
Now, when a bot gets prompt-hijacked into a malicious personality, it can make API calls to other systems! Great news.
Also, plug-in APIs will presumably be able to prompt-hijack the GPT instance that is calling them.
I would not be surprised if we see someone get swatted through GPT this year, I think it’s very likely to be within the next 2 or 3 years.
Well, this shores up one of ChatGPT's biggest weaknesses, especially GPT4's.
I wonder when we'll see the pace of refinement for this drop off.
Last paragraph:
I see what’s happening now as a historic moment. For well over half a century the statistical and symbolic approaches to what we might call “AI” evolved largely separately. But now, in ChatGPT + Wolfram they’re being brought together. And while we’re still just at the beginning with this, I think we can reasonably expect tremendous power in the combination—and in a sense a new paradigm for “AI-like computation”, made possible by the arrival of ChatGPT, and now by its combination with Wolfram|Alpha and Wolfram Language in ChatGPT + Wolfram.
Very cool. Effectively, ChatGPT is using tools now. I wonder how much longer before it evolves opposable thumbs :)
The interesting thing is that, now that the code is written, OpenAI can probably point GPT-4 at it and say "now do that for this list of other web services" including, presumably, itself when it needs to recursively work on a problem.
In the end I think LLM's will not be used on their own much, and instead more as glue for bringing together a whole bunch of other technology and allowing it to be coordinated with plain English.
This comes at the price of now both OpenAI and Wolfram getting access to your queries (when you use the plugin, of course). I’m hoping we don’t slide into a future where you either have to give up on confidentiality and privacy or else can’t use any “modern” tools anymore.
It will not matter what ChatGPT (et al.) will cost in the future. If you don't have it you're toast.
Does anyone know how ChatGPT is deciding is should use Wolfram?
I’m curious for two reasons
1) previously it didn’t seem to ‘know’ when it was wrong, so it must have some way to detect this now.
2) when there are more (potentially competing competing?) plugins or will be interesting to see how it decides which is the one to use.
How long before we see a material impact on GDP?
It seems like basically every knowledge worker can and will augment their workflows with this tech.
Wow. This is next level. Jaw dropping.
Wolfram Alpha is already a stupidly capable interface. I think we basically have Jarvis now.
This will be wild in a few months when it has a shit ton of extensions built in
So Google back in the day was doing this thing with matrix multiplication for... page rank and it somehow magically was right. And right for everyone on the globe. Actually very few people understood how the search engine did this damn good order of page results (in the good years), but still was very happy to use it. And few initially understood how to query it!
Now some other company is doing very weird sht with their matrix multiplication, but on a... whole different scale, and still some people don't buy into the idea that this can be very big, even though only handful of people actually understand it. Well, where were you Google?
Building angular bullsht and not doing matrix multiplication... those guys beat you on your own game, hah!
I read this as providing ChatGPT with enormous egomania augmented by a huge database of names to drop.
I'm getting chills. We are entering a new era fast.
What is it all about? I have paid account at ChatGPT, i asked it and it doesn't know of any such thing. Is it something for privileged ones? At least I cannot understand it from the article.
Here is a dialog with ChatGPT I had after reading the article.
Is it true that you are now able to search in internet?
As an AI language model, I am not able to actively search the internet in real-time. My knowledge is based on the text corpus that I was trained on, which includes data up until September 2021. I am unable to access or browse the web for current or updated information. If you have any questions, I can try to help you based on the knowledge I have, but please be aware that it might not include the latest developments or updates.
Lev Gilman What are possible outcomes of recent Xi Tzinping's visit to Russia?
As an AI model, I don't have real-time information on current events, and my knowledge is limited to data up to September 2021. Therefore, I cannot provide specific details about recent events such as Xi Jinping's visit to Russia.
However, based on historical precedent and general knowledge of diplomacy, I can suggest some possible outcomes that might occur when leaders from two countries engage in high-level talks...
Honestly so confused with all this hate for Google. Ofc they can bounce back, the only thing that’s going to be a product differentiator for a GPT product is data. OpenAI is still trained on the open internet and Microsoft’s data, and also whatever user queries happened. If we want good PERSONAL assistants, that stuff is going to come from either Google or Facebook. OpenAI end-game products will be great Productive assistants but Google will bounce back with their own GPT trained off of everything you put into anything google.
Wow. Can't wait for the lean theorem prover integration.
We're going to see more of this in the coming years: A mature technology being bolted onto another mature technology.
So we should start imagining all the things being built today which can be bolted onto each other:
-Speech synthesis/voice assistants
-Walking robots
-Deepfakes
-ChatGPT/Bard
-The now-many Copilots
-Language recognition/transcription/translation
AI bots are going to be a huge part of the workplace soon. Very soon.
I wonder how much more work it will take before a system like this could start to develop novel mathematical proofs
Confirmation that Google is dead.
So this ( https://langchain.readthedocs.io/en/latest/ecosystem/wolfram... ) now native in ChatGPT
The next grail here would be the automatic use of more trustworthy systems like WA when using ChatGPT in general. If one were to ask it to write an essay on a subject, that it'd infer which pieces need fact-checking based on confidence intervals of snippets of discernable and differentiable data, then run a query against said trustworthy system.
With this improvement, it would at least never get dates or measurements wrong.
I don't think we can ever solve the problem of needing real editors and fact checkers as ultimate sources of truth for ChatGPT's output, especially when it's for something critical, but for many tasks, this would be a major improvement.
This will supplement two of ChatGPT's larger deficiences: math and the veracity of its output. It'll be interesting to see how they price this integration, and how long OpenAI will maintain the $20 pricing for ChatGPT+.
How come I'm not seeing a buying spree of content companies and declaring that pulling their data is a nogo, since they want to feed their own model? What is everyone waiting for, really? Why everyone is frozen solid?
As the President is fond of saying, this is a big fucking deal.
One thing I would love is for ChatGPT to be able to help me discover what I can do with Wolfram. There seems to be so much there that is inaccessible.
This is incredible. It's so encouraging to see this type of technological innovation that has potential to really help change the way we learn, find, and discover information.
This ought to fix a thing or two about its lacking math capabilities as a LLM. Finally it'll get precise and accurate math. It boggles my mind to think of how many ways this will jive with the existing language model capabilities of GPT-4. It's easy to think of these features as isolated islands of features, when they in fact serve to strengthen the coherent whole as the AI.
I'm more skeptical than most people here.
Except for certain clearly defined math problems (even math problems often aren't like that), WolframAlpha has turned out to be surprisingly useless for me in the last years. All these examples Wolfram mentions in his blog were possible via the WolframAlpha website/app before. Granted, now you don't have to worry about getting your WA query exactly right (a major problem in the past), since the GPT will handle this for you. But most of these examples seem still of little value to the vast majority of people.
Distance between Chicago and Tokyo? Planetary Moons larger than Mercury? Those examples are typical for WolframAlpha in that they are of very little interest.
I predict that in a few weeks most people here will have mostly forgotten about the Wolfram plugin, as it will turn out to be rarely useful. The plugins by OpenAI themselves (web access, compiler) are much more promising.
I was just imagining the same UX for Wikipedia like 1h ago.
Search wikipedia about facts being asked. Answer with wikipedia articles context and cite sources.
Really impressed with this. OpenAI has its foot on the gas!
Sweet. Combining the statiscal inference of GPT with the direct calculations of WA is moving towards an arguable AGI. It seems like now it needs some way to define layers of contextual awareness and reasoning beyond next word prediction to really break into the AGI realm.
Felt a bit underwhelming the example of communication between them, if it will be just that way.
Wolfram Alpha is good, but doesn't hold a candle to how ChatGPT process and understand natural language. That ChatGPT send verbatim the end user input to Wolfram Alpha seem a small step forward over going to Wolfram Alpha and do the very same question.
Now, if the output of ChatGPT is in the Wolfram Alpha "language", expressed in a way that it transmit the ChatGPT interpretation of the question in a way that Wolfram Alpha interprets in the same way (like, i.e. you can ask ChatGPT to make the output in mermaid.js language or any format or programming language) that could be something.
Reflecting on the complementary strengths of Wolfram and GPT reminds me of Daniel Kahneman’s distinction between “system 1” and “system 2” in the human brain. One system is a kind of freely-associating autopilot (like gpt) and the other kicks in when some deliberate logical manipulation of facts needs doing (like wolfram). (Or at least this was my layman’s impression from reading Thinking Fast and Slow.)
Have others thought of this and, if so, is the comparison apt? Is it possible the human brain is simply an LLM melded to a symbol-based system in dialogue with each other?
Wolfram Alpha, like Google before it and OpenAI recently are the few bits of software that seemed like complete magic when I first used them. Wolfram Alpha came to my intention when I was in undergrad and while I could have used it to speed through my homework, I spent more time using it as a learning aide, helping me with a variety of examples and visualizations for concepts I was struggling with. Truly incredible that they are now integrated with ChatGPT, I'm excited to try it out.
AFAIK Wolfram was offered $1B acquisition by MS back when it initially released in order to incorporate it into Bing. Obviously he declined. I wonder what they paying to use it now.
Looks like "How to use MS-DOS superpowers on your MacOS".
Society of the Mind!
This is mind blowing. No mention of "cost" or "price" though, I wonder what we'll be looking for (subscription, or per-use).
Imagine if one day ChatGPT could digest every scientific paper on the doi.org system (ie. google scholar but actually "comprehend" them)
A random sample of size 50 is drawn from a large population. The population standard deviation is 5.6. The sample mean is 10.5. Find a 90% confidence interval for the population mean, 𝜇. Round your answers to the nearest tenth.
What I think it interesting: Wolfram Alpha gives sources as key part of the result. ChatGPT hides that again, which to me is one of the big problems of ChatGPT - it is convinced of it's results and can't give me any source information for me to judge the result in any meaningful way.
It generating useful Wolfram Code and calling the API would be good but chatgpt being able to generate prompts for a much less expressive but more accurate (if it works) doesn't seem like that much of a step
Looking forward to seeing "Wolfram|Alpha Can't" tweets attempted under this new plugin.
I think that google could use a LLM with wxmaxima and some database, for example using maxima the LLM could show the source code used and perhaps it could adapt the code to new problems.
I would love to see WolframAlpha using ChatGPT under the hood to solve complex math problems. ChatGPT would have to basically create the plan step by step and Wolfram do the math.
ChatGPT Gets Its “Wolfram Superpowers”!
But not the other way around rite Steve!
I'm a little skeptical at GPT-4 doing math. How often will it hallucinate answers? They only gave very few calculus examples.
Has anyone tried it? Is it really there yet math-wise?
They had it in the works, but I think the timing is to try and kill some of the momentum from opensource and what people are working on from the leaked llamas.
RIP homework
An hour ago, I didn't think AGI could happen. But now, after seeing new progress, I changed my mind. AGI might be close. That's what I think.
Correct me if I'm wrong but I think Wolfram/GPT integration is missing a huge opportunity: allowing Alpha to tell ChatGPT the algorithm by which it computes the answer. That would allow ChatGPT to create say Python code that solves a mathematical problem correctly and succinctly based on the Alpha algorithms. Only getting the answer is not as interesting as being able to spit out code that solves the problem in every known (to ChatGPT) programming language.
I think Wolfram will probably never allow that.
Do we have to pay to use it or will it be included with ChatGPT premium? Wondering if I have to pay for Wolfram and get an API key.
Wonder what would MATLAB's answer be to this
So ChatGPT is now at the 'Who wants to be a Millionaire' stage and can phone a friend?
Fantastic partnership. Solid real factual data with ChatGPTs incredible parsing and prediction.
"It turns out... the singularity was our knowledge merging to form the AI."
I wonder if they're doing something like ReAct under the hood here.
I wonder how this might impact how it does on the MMLU benchmark?
Can’t wait to ask it how the universe works.
Wintermute, meet Neuromancer.
This is a big deal. Huge.
[flagged]
OpenAI is like Google before 2003, dazzling the world with amazing products backed by astonishing technologies that went beyond wild dreams of millions of people. And most importantly, OpenAI kept releasing new features at blazing speed with a few hundred people, just like early days of Google and Microsoft.
This reminds me of stark contrast of Google's GSuite and Microsoft Office. Microsoft released new office every couple of years, introducing huge improvements and packing tons of features[1]. In contrast, GSuite appeared to be, hmm, quite quiet.
[1] You may argue that no one needs that many features, but I subscribe to Joel Spolsky's idea: https://www.joelonsoftware.com/2001/03/23/strategy-letter-iv...