AI & ML interests

8b·is builds 100% offline-first sovereign intelligence (ALEXIAI <3), bare-metal pure-Rust cognitive wave memory (MEM|8), O(1) integer acoustic salience (Marine & Qwave), and hardware-verified machine-code capsules (g8t·is). Zero third-party cloud LLM lock-in. Zero runtime dependencies. Zero floating-point drift.

Recent Activity

PeetPedro  published a Space 3 days ago
eightb/README
View all activity

PeetPedro 
published a Space 3 days ago
PeetPedro 
posted an update 3 months ago
view post
Post
164
# 🌌 PeetPedro — Hugging Face Sovereign AI Profile

**Identity:** Peter Lodri (PeetPedro / pocok0xRE / 0xp3t3rl)
**Focus:** BitNet b1.58 Ternary Weight Quantization, Metal GPU SIMD Operators, Sovereign AI Systems

---

## 🚀 Spaces & Models
- **[PeetPedro/axiom-quant-demo]( PeetPedro/axiom-quant-demo: Live Gradio interactive space demonstrating BitNet b1.58 ternary weight operator algebra and SIMD contractions.

---

## 📊 Datasets & Research Papers
- **[PeetPedro/axiom-quant-constellation]( PeetPedro/axiom-quant-constellation: Research monograph series PDF, TeX sources, and 7 high-resolution architectural infographics.
- **[PeetPedro/ultrawhale-dogfood]( PeetPedro/ultrawhale-dogfood: 24.8 MB synthetic Q&A fine-tuning dataset for BitNet b1.58 dogfooding.
- **[PeetPedro/kompress-ultra-bitnet-benchmarks]( PeetPedro/kompress-ultra-bitnet-benchmarks: Layer-by-layer weight sparsity & SVD energy decay JSON metrics.

---

## 🌐 External Constellation Links
- **Public Innovation Portal:** https://portail-vaked-dev.pages.dev/showcase.html
- **WASM SIMD Sandbox:** https://portail-vaked-dev.pages.dev/sgc_wasm_demo.html
- **Research Monographs:** https://axiomquant.org/
- **GitHub:** https://github.com/peterlodri-sec

*the constellation · 0 + 1 · fine touch from within · vaked.dev*
  • 39 replies
·
PeetPedro 
posted an update 4 months ago
PeetPedro 
posted an update 5 months ago
PeetPedro 
posted an update 5 months ago
view post
Post
165
hey, I'm doing some experimenting, looping around :slight_smile:
---
**kompress-v6** *shipped* — trained on Claude Code agent patterns (bash output, file reads, stack traces, search results, JSON tool responses). 3k synthetic pairs + 2k existing, fine-tuned from v4, $0.20 on vast.ai.

Results:
heretic exact_pct 0.962 (v4: 0.967),
keep_rate 0.854 (v4: 0.823),
override delta 0.
Model got more conservative — higher keep_rate on structured technical content.
Real proxy:
v4 compressed 9.5%,
v6 compressed 4.2% on the same session.
Less aggressive, fewer must-keep tokens dropped on paths and identifiers.

Interesting failure: self-labeling with v4+override collapsed mk_in_ref to 0.652.
TokenExpiredError splits into Token+Expired+Error — subtokens that don't individually match the must-keep regex, so the force-keep never fires. Generator references (mk_in_ref=1.0 by construction) ended up being better labels than v4's compressed output for agent data.
Fix for next run: slide a 2-3 subtoken window instead of checking individual subtokens. Would let self-labeling work on agent content and potentially produce a more compression-aggressive v7.

Models on HF:
- PeetPedro/kompress-v6
- PeetPedro/kompress-v4
- PeetPedro/kompress-v3
Write-up: https://pocoo.vaked.dev/posts/2026-06-25-kompress-v6-agent-distribution