SymbolicAI: A neuro-symbolic perspective on LLMs

Post by futurisold » Fri, Jun 27, 2025, 11:28 PM UTC

krackers wrote: post #19

futurisold wrote: post #14

Earlier quoted context omitted.

Thank you! I'm not familiar with that project, will take a look

Some of this seems a bit related to Wolfram Mathematica's natural language capabilities. https://reference.wolfram.com/language/guide/FreeFormAndExte... It can (in theory) do very similar things, where natural-language input is a first class citizen of the language and can operate on other objects. The whole thing came out almost a decade before LLMs, I'm surprised that they haven't revamped it to make it really shin…

Post by futurisold » Fri, Jun 27, 2025, 11:39 PM UTC

VinLucero wrote: post #16

Nice! But have you considered a Neurosymbolic AI that can Evolve? https://deepwiki.com/dubprime/mythral/3.2-genome-system Or feel Emotion? https://deepwiki.com/search/how-do-emotives-work_193cb616-54... Have you read Marvin Minsky’s Society of Mind?

Post by VinLucero » Fri, Jun 27, 2025, 11:59 PM UTC

futurisold wrote: post #23

VinLucero wrote: post #16

Nice! But have you considered a Neurosymbolic AI that can Evolve? https://deepwiki.com/dubprime/mythral/3.2-genome-system Or feel Emotion? https://deepwiki.com/search/how-do-emotives-work_193cb616-54... Have you read Marvin Minsky’s Society of Mind?

Shortly, yes to all. We actually had an experiment going from theory of mind to emotion, but it's hanging right now since I feel the models aren't quite there yet and it yields diminish returns relative to effort. But could easily be revived. Minsky isn't my fav though, I'm leaning more toward Newell/Simon and friends from that generation.

Post by futurisold » Sat, Jun 28, 2025, 12:15 AM UTC

VinLucero wrote: post #25

futurisold wrote: post #23

Earlier quoted context omitted.

Shortly, yes to all. We actually had an experiment going from theory of mind to emotion, but it's hanging right now since I feel the models aren't quite there yet and it yields diminish returns relative to effort. But could easily be revived. Minsky isn't my fav though, I'm leaning more toward Newell/Simon and friends from that generation.

@futurisold, would love to collaborate with your team on running experiments. We have $300k of GPU credits to burn in the next 2 months. There’s only so many cat videos my Agentic AI Army can create: https://youtu.be/upVY1QioDeY?si=H566-_JIm7FmW4u0

Post by haileys » Sat, Jun 28, 2025, 12:38 AM UTC

sram1337 wrote: post #2

This is the voodoo that excites me. Examples I found interesting: Semantic map lambdas S = Symbol(['apple', 'banana', 'cherry', 'cat', 'dog']) print(S.map('convert all fruits to vegetables')) # => ['carrot', 'broccoli', 'spinach', 'cat', 'dog'] comparison parameterized by context # Contextual greeting comparison greeting = Symbol('Hello, good morning!') similar_greeting = 'Hi there, good day!' # Compare with specific…