Group Abstract Group Abstract

Message Boards Message Boards

Is Wolfram Siri-ous about AI?

POSTED BY: Jonathan Kinlay
6 Replies

Stephen Wolfram just published a new article:

Wolfram|Alpha as the Way to Bring Computational Knowledge Superpowers to ChatGPT

https://writings.stephenwolfram.com/2023/01/wolframalpha-as-the-way-to-bring-computational-knowledge-superpowers-to-chatgpt

We started a new dedicated discussion here:

Stephen Wolfram on ChatGPT, Wolfram|Alpha & Computational Knowledge
https://community.wolfram.com/groups/-/m/t/2763581

POSTED BY: EDITORIAL BOARD

From Stephen Wolframs’s latest writings

What about ChatGPT directly learning Wolfram Language? Well, yes, it could do that, and in fact it’s already started. And in the end I fully expect that something like ChatGPT will be able to operate directly in Wolfram Language, and be very powerful in doing so. It’s an interesting and unique situation, made possible by the character of the Wolfram Language as a full-scale computational language that can talk broadly about things in the world and elsewhere in computational terms.

Q.E.D.

Nice to find oneself talking to something other than a brick wall, for once.

POSTED BY: Jonathan Kinlay
Posted 2 years ago
POSTED BY: Alec Graves
Posted 2 years ago

Also there is this beautiful work that was uploaded to YouTube yesterday:

"Natural Language Processing Template Engine" by Anton Antonov (YouTube)

I agree with many of the points made regarding ML and NLP. A super smart template engine is a very powerful and repeatable method for code generation. Add some ML template selection and improve the output filtering, and you have something that could rival CoPilot's 25% acceptance rate in many instances.

POSTED BY: Alec Graves
POSTED BY: Jonathan Kinlay
Posted 2 years ago

I agree that more should be done with NLP and code completion, as this is a path towards widespread end-user programmability and language adoption.

Programming languages are fundamentally about representing an abstract computer that developers know how to talk to and which is ideally easier to talk to than the underlying hardware. Language models have demonstrated an ability to... well... model language, and thereby provide code that appears correct in the context of an input prompt. I think we are still far away from a system that can generate programs that solve real-world problems given natural language inputs from inexperienced end users (and honestly, Wolfram Alpha is probably closer to that than CoPilot for many problems). Even the results from co-pilot are only accepted about 25% of the time according to GitHub's CoPilot FAQ - and I would bet over 95% of accepted results required further modification from an experienced developer to actually solve the problem at hand.

I believe the value of tools like CoPilot or Wolfram|Alpha-mode notebooks rests largely in their ability to teach elements of syntax and style of a new programming language to unfamiliar developers. This will likely be quite similar to how artists use reference images or developers in the distant, pre-AI past used Stack Overflow, tutorials, and documentation examples.

Beyond that, the difficult part of programming is not typing the syntax. I think it is instead figuring out what problem you want to solve and how to integrate that solution into the larger system in a coherent way. I believe doing this will always take a lot of effort, though I am hopeful that machines might eventually do some more heavy lifting. I think better starting points generated by language models would have a chance to improve developer productivity, just as an artist starting by tracing an image will be able to finish much faster than one starting from a blank canvas. However, I do worry that over-reliance on that starting point will result in an increase in needless complexity (and associated errors) and a stagnation in style.

Anyway, I think Wolfram|Alpha notebooks could use some serious machine learning NLP upgrades. Co-Pilot-style code generation and output filtering could pave the way to greatly increasing the number of inputs that can be turned into valid code. Also, while Wolfram Language does not have the largest dataset around, it certainly has one of the highest-quality and cleanest datasets: look at the documentation and Mathematica Stack Exchange answers!

POSTED BY: Alec Graves
Reply to this discussion
Community posts can be styled and formatted using the Markdown syntax.
Reply Preview
Attachments
Remove
or Discard