Adventures in Symbolic Algebra with Model Context Protocol

118 포인트작성자: freediver3일 전

16 comments

I really appreciate Stephen's mixture of skepticism combined with genuine interest in experimenting with these tools. Most MCP posts I've read have been so much hype I've been left with no clue what MCP actually does. This is the first article I've read on the topic that earnestly makes me want to start messing around with MCP for fun (and makes it clear how to get started).It's a bit unfortunate that the field is so dominated by extremes of hype and skepticism, both of which aren't particularly helpful to getting problems really solved.

评论 #44066080 未加载

behnamoh3일 전

So, we’ve come full circle to symbolic AI! This article essentially suggests that LLMs could be effective translators of our requests to command-line code or input to symbolic AI software, which would then yield precise solutions. However, I feel this approach is overly mechanical, and I don’t believe AGI would be achieved by creating thousands, if not millions, of MCP servers on our machines. This is especially true because MCP lacks scalability, and anyone who has had to send more than three or four function schemas to a language model knows that excessive JSON schema complexity confuses the model and reduces its performance.

评论 #44071515 未加载

评论 #44064004 未加载

评论 #44073331 未加载

arunbahl3일 전

Awesome stuff! We use a similar approach (without MCP) to great effect with Prolog currently and feels like we're only just starting to scratch the surface here.A great paper from Nasim Borazjanizadeh and Steven Piantadosi at UC Berkeley for those interested: Reliable Reasoning Beyond Natural Language <a href="https://arxiv.org/abs/2407.11373" rel="nofollow">https://arxiv.org/abs/2407.11373</a>For anyone digging in who wants to hack on this: arun [at] aloe.inc

tpurves3일 전

Wonderfully cheeky but also helpfully informative writeup. Also appreciate the hat-tip to all the (as yet) unsolved security issues. Clearly MCP is onto something important, although undoubtedly the standard (or some replacement standard) will mature a fair bit before we're done with it. The flip side to that is, MCPs are probably as 'easier' to experiment with now than they are ever going to be.

FilosofumRex3일 전

<pre><code> > So, we’ve come full circle to symbolic AI! </code></pre> Yes, but from a business point of view, NLP based GUIs have been the holy grail of marketing and customer support, especially in STEM apps market.Case in point, Wolfram Alpha is not much more than an attempt to market Mathematica to lazy and failing college students. If that cost, and localization, can be offloaded to LLMs as the universal front end to technical software, it'd free up SWE resources to focus on core functionality.If Magma, my favorite math/cryptography tool, had an LLM frontend, I could save time wasted onboarding new cryptographers.<a href="https://magma.maths.usyd.edu.au/calc/" rel="nofollow">https://magma.maths.usyd.edu.au/calc/</a>

Hugsun3일 전

I was very pleased to discover that Mistral's Le Chat has inbuilt support for python code execution and sympy is importable.It will regularly use it and reliably when asked to.

jgalt2123일 전

> But let's not let a potential rootkit get in the way of a fun weekend experiment.Great quote.

mhh__3일 전

I like this type of flow.On tensor notation: Tensor indices aren't bad (a good notation should guide a calculation and they do) but I can't help but feel they're far too error prone.What are the alternatives? Penrose diagrams?

评论 #44071410 未加载

amelius3일 전

How does the LLM know that it can use the factor tool to factor integers? Just by looking at the string "factor an integer"?

评论 #44065030 未加载

评论 #44063758 未加载

评论 #44063837 未加载

ash-ali3일 전

I think this is the proper way to use llms for tasks that require high fidelity. currently im working on binary analysis using llms for natural language and letting ghidra/codeql do the symbolic work. scalability is a massive issue, perhaps the biggest besides fidelity.its interesting to see many people come to the same neuro-symbolic conclusion around the same time.

hosolmaz2일 전

It might make more sense to give the model a Jupyter Notebook/code interpreter MCP as a more general case. The environment would have to have sympy, numpy, scipy, matplotlib etc. installed of course

rudi_mk2일 전

Damn. I started building exactly the same thing a couple weeks ago.<a href="https://github.com/equationscp/equationscp">https://github.com/equationscp/equationscp</a>

nickysielicki2일 전

bit more fleshed out than what I slopped together last month for this: <a href="https://github.com/sielicki/dogfood/blob/master/scripts/mcp-server-sympy.py">https://github.com/sielicki/dogfood/blob/master/scripts/mcp-...</a>I've found it useful for thought experiments around trading.

0cf8612b2e1e3일 전

Tangentially, are there any symbolic algebra systems that can handle millions of equations?I have never used a symbolic algebra system, but came across a problem where I am trying to model a deterministic simulation system. I can write out the computation graph (~20 million equations for final state), but Sympy chokes on seemingly dozens of symbols. No hope of processing the final state or being able to express a simulation state in terms of my desired input variables.Not sure if my expectations are mismatched with reality, I am hugely bungling the tool, or Sympy has laughable performance vs the more capable commercial options.

评论 #44068521 未加载

评论 #44066128 未加载

Iwan-Zotow3일 전

Curious if this could be done for Mathematica. SymPy is kind of ...

评论 #44072058 未加载

rjeli3일 전

the implementations have a distinctly "I wrote this at a 3 AM hackathon" vibeThe LLM handles the natural language interaction and orchestration, while the computer algebra system does what it does best ... exact symbolic manipulation.this smells like claude :D