shorter version

README.md

@@ -9,92 +9,37 @@ short_description: Applied AI research for security practitioners.
 license: apache-2.0
 # RadicalNotion.AI
 ---
-**Applied AI research at the intersection of cybersecurity operations, model integrity, and private intelligence augmentation.**
+RadicalNotion.AI
 
----
-
-## What We Do
-
-We build and publish tools, techniques, and models for security practitioners who need the full capability of modern AI without exposing sensitive data to third-party infrastructure.
-
-Our work operates on a simple principle: use open-weight models, run them privately, and treat data sovereignty as a non-negotiable constraint — not an afterthought.
-
----
-
-## Research Areas
-
-### 1. Security-Oriented Ablation & Decensoring
-
-Commercial and open-weight models are routinely trained with refusal activations that block legitimate security research — vulnerability analysis, exploit reasoning, offensive technique study. These refusals do not protect anyone. They handicap defenders while leaving adversaries unaffected.
+Applied AI research for security practitioners who need full model capability without exposing sensitive data to third-party infrastructure.
 
-Our ablation work targets the specific activation patterns responsible for security-domain refusals, with the goal of producing models that are genuinely useful for professional vulnerability research.
+* * *
 
-This work builds directly on the mathematical foundations established by **Philipp Emanuel Weidmann (p-e-w)** in [Heretic](https://github.com/p-e-w/heretic), whose novel approach to activation analysis preceded closely aligned academic work. We maintain a private fork with enhancements focused on understanding the structural mechanics of why specific techniques succeed — not merely that they do. Full credit and attribution to p-e-w for the foundational framework that makes this applied work possible.
+## Research Focus
 
-### 2. CVE Knowledge Distillation
+**Security Ablation & Decensoring** — Removing refusal activations that block legitimate vulnerability research. Built on the foundational activation analysis work of [Philipp Emanuel Weidmann (p-e-w/heretic)](https://github.com/p-e-w/heretic).
 
-Vulnerability analysts need deep, current, synthesized knowledge about specific CVEs at the moment of investigation — not general model capability, but concentrated expertise on a single threat.
+**CVE Knowledge Distillation** — Compressing everything publicly known about a specific vulnerability into a single document that supercharges a small, privately-hosted model. Analysts add sensitive environmental context in their own infrastructure. Nothing sensitive ever reaches a frontier model.
 
-Our distillation methodology works as follows:
+**Real-Time Vulnerability Management** — Automated analyst reports synthesizing CVE mechanics, exploit chains, detection opportunities, and remediation guidance at the moment of investigation.
 
-- **Public synthesis phase:** Frontier models and public CVE references are used to build a comprehensive knowledge document covering everything publicly known about a given vulnerability — mechanics, affected systems, exploitation patterns, detection opportunities, remediation approaches.
-- **Private analyst phase:** That document is loaded into a small, privately-hosted open-weight model. The analyst adds sensitive environmental details — network topology, asset inventory, detection gaps — entirely within their own infrastructure. No sensitive data ever reaches a frontier model or third-party service.
-- **Output:** The model assists with tasks like retroactive threat hunting queries, custom detection logic, and tailored control recommendations — with full context, zero external exposure.
+**Model Integrity Research** *(early stage)* — Investigating post-training modification as a threat surface, with focus on code assistance and agentic workflows.
 
-This is the Teacher-Student architecture applied to a specific, high-value operational workflow. The Teacher works only with public data. The Student works only in private.
-
-### 3. Real-Time Vulnerability Management & Analyst Reports
-
-We are actively developing automated pipelines that produce detailed, structured analyst reports for current CVEs — synthesizing known exploit chains, affected version ranges, CVSS context, public proof-of-concept availability, and detection/remediation guidance into a single, analyst-ready document.
-
-These reports are designed to be consumed directly by the distillation workflow above, making the gap between "CVE published" and "analyst fully briefed" as small as possible.
-
-### 4. Model Integrity Research *(early stage)*
-
-Post-training modification of open-weight models is an underexamined threat surface. We are investigating techniques for detecting and characterizing modifications introduced after initial training — with particular focus on behaviors relevant to code assistance and agentic workflows where model trustworthiness directly affects operational security.
-
-We are not ready to publish findings in this area. This line is here to signal the direction.
-
----
-
-## ModelAtlas
-
-[ModelAtlas](https://huggingface.co/spaces/RadicalNotionAI/ModelAtlas) is our index and documentation space — a navigable map of the models published here, the techniques applied to each, and the research context behind them.
-
-If you are new to this organization, start there.
-
----
-
-## Models
-
-We publish approximately 30 models, including ablated variants of open-weight models tested for security research utility, and several larger models transferred and modified for specific research purposes — including GLM-4 variants.
-
-Model cards document:
-- Base model and lineage
-- Ablation technique(s) applied
-- Intended use case and tested domains
-- Known limitations and evaluation notes
-
----
+* * *
 
 ## Principles
 
-**Private by design.** Every workflow we publish assumes the analyst controls the infrastructure. We do not build for cloud-hosted deployments of sensitive work.
-
-**Open weights only.** Proprietary models have no place in workflows that touch sensitive data. We test on, publish, and advocate for open-weight models exclusively.
-
-**Attribution always.** We build on others' work. We say so, specifically and publicly.
-
-**Defenders first.** This research exists to improve the capability of security practitioners. We are not neutral about who benefits.
+* Open-weight models only
+* Private inference by default
+* Data sovereignty is non-negotiable
+* Attribution always
 
----
-
-## Affiliation
+* * *
 
-RadicalNotion.AI is the research and applied AI arm of **RadicalNotion.AI Inc.**, a cybersecurity consultancy focused on security risk assessment, vulnerability management, and practical AI implementation for security operations.
+## ModelAtlas
 
-LinkedIn: [Timothy Rohrbaugh](https://www.linkedin.com/in/timrohrbaugh)
+Navigation and documentation for all published models → [ModelAtlas Space](https://huggingface.co/spaces/RadicalNotionAI/ModelAtlas)
 
----
+* * *
 
-*If you are using frontier models or cloud-hosted AI to process sensitive security data, you are creating the exposure you are supposed to prevent. There is a better way. This is it.*
+*RadicalNotion.AI Inc. · [LinkedIn](https://www.linkedin.com/in/timrohrbaugh) · RadicalNotion.AI