4 comments

  • WFGY 10 hours ago

    I'm the original author of this open-source reasoning engine.

    What it does: It lets a language model *close its own reasoning loops* inside embedding space — without modifying the model or retraining.

    How it works: - Implements a mini-loop solver that drives semantic closure via internal ΔS/ΔE (semantic energy shift) - Uses prompt-only logic (no finetuning, no API dependencies) - Converts semantic structures into convergent reasoning outcomes - Allows logic layering and intermediate justification without external control flow

    Why this matters: Most current LLM architectures don't "know" how to *self-correct* reasoning midstream — because embedding space lacks convergence rules. This engine creates those rules.

    GitHub: https://github.com/onestardao/WFGY

    Happy to explain anything in more technical detail!

  • NetRunnerSu 11 hours ago

    If you can't even do the prompt engineering to adapt the AI to HN's style, it's hard to believe that you're doing this work in any meaning

    • WFGY 11 hours ago

      Actually I am really new to here. I will check the rules

  • WFGY 11 hours ago

    welcome to leave any message here