Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Making Wolfram tech available as a foundation tool for LLM systems

writings.stephenwolfram.com

Post reply on HN
Print view View original

41–50 of 188 posts

Re: Making Wolfram tech available as a foundation tool for LLM systems

#41

Post by porcoda »

petcat wrote: post #2

Sounds cool. Aside, I hate the fact that I read posts like these and just subconsciously start counting the em-dashes and the "it's not just [thing], it's [other thing]" phrasing. It makes me think it's just more AI.

The em-dash metric is silly. Some people (including me) have always used them and plan to continue to do so. I just pulled up some random articles by Wolfram from the before-LLM days and guess what: em-dashes everywhere. One sample from 2018 had 89 of them. Wolfram has always written in the same style (which, admittedly, can be a bit self-aggrandizing and verbose). It’s kinda weird to see people just blowing it off as AI slop just because of a —.

Re: Making Wolfram tech available as a foundation tool for LLM systems

#42

Post by lcdryuga1983 »

kylecazar wrote: post #25
nphardon wrote: post #15

There's a great discussion with Stephen Wolfram on the Sean Carroll podcast. Listening to it made me think very highly of Wolfram. He's a free thinking, eccentric, mathematician, scientist; who got started doing serious work at a very young age. He still has a youthful creative approach to thought and science. I hope LLMs do pair well with his tools.

He live streams the (internal) Wolfram Alpha product meetings on YouTube. It's really interesting to watch, I've been a fly on the wall for years.

I tried finding this but couldn't find them on youtube. Can you please share the link for one of the videos?

Re: Making Wolfram tech available as a foundation tool for LLM systems

#44

Post by troymc »

maxdo wrote: post #29

CAG sounds like fake solution for LLM's. Math problems are not custom data, they are limited in amount, and do not refresh like product manuals. Hence math can always be part either generic llm or math fine tuned llm, without weird layer made for human ( entire wolfram) and dependencies. Wolfram alpha was always an extra translation layer between machine and human. LLM's are a universal translation layer that can als…

You wouldn't use an LLM to solve a big Linear Programming problem, because it would cost way more than using the Simplex Method, and you'd be worried that it might be wrong.

Re: Making Wolfram tech available as a foundation tool for LLM systems

#45

Post by fragmede »

Davidzheng wrote: post #40

There's a lot of value in the implementation of many strong and fast algeorithms in computer algebra in proprietary tools such as Maple, Wolfram, Matlab. However, I (though of course believe that such work needs to be compensated) find it against the spirit of science to keep them from the general public. I think it would be good service to use AI tools to bring open source alternatives like sympy and sage and macaul…

> against the spirit of science

Unfortunately, the bank doesn't accept spirit of science dollars, and neither does the restaurant down the street from me either.

Re: Making Wolfram tech available as a foundation tool for LLM systems

#46

Post by closeparen »

currymj wrote: post #18
mr_mitm wrote: post #11

Earlier quoted context omitted.

Back when I was using it, mathematica was unmatched in its ability to find integrals. Has python caught up there?

sympy is good enough for typical uses. the user interface is worse but that doesn't matter to Claude. I imagine if you have some really weird symbolic or numeric integrals, Mathematica may have some highly sophisticated algorithms where it would have an edge. however, even this advantage is eaten away somewhat because the models themselves are decent at solving hard integrals.

I like to think of Claude as enjoying himself more when working with good tools rather than bad ones. But metaphysics aside, tools that have the functions you would expect, by the names you would expect, with the behavior you would expect, do seem to be just as important when the users are LLMs.

Re: Making Wolfram tech available as a foundation tool for LLM systems

#47

Post by falcor84 »

fragmede wrote: post #45
Davidzheng wrote: post #40

There's a lot of value in the implementation of many strong and fast algeorithms in computer algebra in proprietary tools such as Maple, Wolfram, Matlab. However, I (though of course believe that such work needs to be compensated) find it against the spirit of science to keep them from the general public. I think it would be good service to use AI tools to bring open source alternatives like sympy and sage and macaul…

> against the spirit of science Unfortunately, the bank doesn't accept spirit of science dollars, and neither does the restaurant down the street from me either.

What does this have to do with anything? We as a culture decided that science is worthwhile, and that it's worth funding it with public money, which I personally strongly support. With that in mind, I want us to continue contributing to making scientific research and the benefits that it provides to be disseminated freely, while also paying good scientists with actual dollars that they could spend in restaurants.

Re: Making Wolfram tech available as a foundation tool for LLM systems

#48

Post by falcor84 »

currymj wrote: post #18
mr_mitm wrote: post #11

Earlier quoted context omitted.

Back when I was using it, mathematica was unmatched in its ability to find integrals. Has python caught up there?

sympy is good enough for typical uses. the user interface is worse but that doesn't matter to Claude. I imagine if you have some really weird symbolic or numeric integrals, Mathematica may have some highly sophisticated algorithms where it would have an edge. however, even this advantage is eaten away somewhat because the models themselves are decent at solving hard integrals.

For numeric stuff, I've been playing recently with chebpy (a python implementation of matlab's chebfun), and am really impressed with it so far - https://github.com/chebpy/chebpy
Post reply on HN