1. Forum
  2. Newsgroups
  3. comp.theory

  • Re: RDFs revenge on the AI Boom [GraphMERT] --- Bridge to LLMreliability

    From olcott@polcott333@gmail.com to sci.logic,sci.math,comp.theory,comp.ai.philosophy on Sun Oct 19 21:48:24 2025
    From Newsgroup: comp.theory

    On 10/19/2025 7:39 PM, Mild Shock wrote:
    Hi,

    Now there is the neuro symbolic hybrid of tripple store and
    artificial neural networks. Already in 2019 proposed an
    embedded attention mechanism by Deepak Nathani et al.:

    GraphMERT: Efficient and Scalable Distillation
    of Reliable Knowledge Graphs from Unstructured Data https://www.researchgate.net/publication/396457862

    Neurosymbolic 80M AI from Princeton beats GPT,
    SuperIntelligence without OpenAI:
    https://www.youtube.com/watch?v=xh6R2WR49yM

    Have Fun!

    Bye

    This is only the exact same idea as my basic
    facts in that the goals are identical. It is
    enormously more advanced than what I have
    because I only have the goal. I basically
    have no idea how to achieve this goal.

    GraphMERT is actually achieving this goal with
    high reliability. This is the exact kind of
    bridge that LLM systems need to eventually
    become extremely reliable.
    --
    Copyright 2025 Olcott "Talent hits a target no one else can hit; Genius
    hits a target no one else can see." Arthur Schopenhauer
    --- Synchronet 3.21a-Linux NewsLink 1.2