Elyan Labs
Published February 12, 2026 | Version v1
Preprint Open

Hardware Entropy Injection for Behavioral Divergence in LLM Inference: The PSE Framework on IBM POWER8

Authors/Creators

  • 1. Elyan Labs (Independent Research)

Description

We present a method for injecting hardware-sourced entropy into LLM inference to produce provable behavioral divergence using the IBM POWER8 mftb (Move From TimeBase) instruction.

Key results:

  • Provable divergence: 3 runs with identical seeds produce 3 distinct MD5 hashes
  • 0.2% overhead: burst strategy (every 4th token, top-512 only) is nearly free
  • 8.81x combined speedup (16.74 to 147.54 t/s) with full PSE stack
  • 4 behavioral metrics defined: NOI, DR, ACS, MCI for entropy-mediated quality

Grounded in Hebbian learning theory and biological stochastic resonance. Part of the Proto-Sentient Emergence (PSE) framework.

Notes

Priority: December 2025 (PSE framework implementation on POWER8). Predates DeepSeek Engram (arXiv:2601.07372) by 27+ days. Source code: https://github.com/Scottcjn/ram-coffers Video evidence: https://youtu.be/T_o39s7r0iE (Dec 17, 2025)

Files

PSE_Hardware_Entropy.md

Files (16.5 kB)

Name Size Download all
md5:a072fff368e56ebce6234acff3d1dd38
16.5 kB Preview Download

Additional details

Related works

Is supplemented by
Software: https://github.com/Scottcjn/ram-coffers (URL)
References
Publication: 10.5281/zenodo.18321905 (DOI)
Publication: 10.5281/zenodo.18623594 (DOI)