Writing Hub
AI governance essays, reasoning systems notes, experiment logs, and technical writing across BioAI and engineering practice.
Project Topics
We Built AI Verification Infrastructure. Then It Found Our Blind Spots.
A technical account of the Flamehaven Verification Ledger — what it found, where it failed, and what we need the field to tell us
The Two Problems No One Talks About in AI Agent Coding Pipelines
AI agent coding pipelines fail not because models are weak, but because verification is structurally broken. This article identifies four empirically documented failure mechanisms — agreement bias, latent entanglement, echoing, and right-for-wrong-reasons — and proposes a concrete architecture: hash-chained audit records, hybrid recurrence scoring, dynamic context budgets, and evidence-first review across three independent axes. Covers multi-agent pipeline design, agentic code review, blueprint indexing, and P0–P4 governance gates.
Stanford. Princeton. A bioRxiv Paper. So Why Did Nobody Ask Where the Data Goes?
BioClaw processes EHR data. Its primary showcase channel is WhatsApp. We audited the repository: 60/100, Tier 2 Caution. Here is what the bioRxiv paper says that the README does not.
Your Bio Repo Could Get You Fined. Here Is Why We Check Every Single One.
When a bio AI repository claims HIPAA compliance but the code says otherwise, the legal exposure falls on whoever deploys it. STEM-BIO-AI evaluated yorkeccak/bio — 322 stars, modern stack, one dangerous README line. Score: 48/100. T1 Quarantine. Full audit report with score matrix, regulatory traceability, and raw machine output.
STEM-BIO-AI Audit Report: yorkeccak/bio
When a README Claim Meets a Deterministic Scanner
From Score to Workflow: Turning STEM BIO-AI Into a Local Audit System
Bio/medical AI trust should not collapse into one score. STEM BIO-AI v1.6.2 shows how deterministic auditing, evidence-led diagnostics, regulatory traceability, and bounded AI advisory can become an inspectable local workflow.
Each /slop Is a Calibration Signal — AI-SLOP Detector v3.6.0 and the Claude Code Skill
Every /slop invocation records to a project-scoped history. After 10 re-scanned files, bounded self-calibration adjusts detection weights for your codebase. Here is the mechanism, the data, and what actually shipped in v3.6.0.
How Do You Trust the AI Auditor? STEM-AI v1.1.2 and Memory-Contracted Bio-AI Audits
STEM-AI v1.1.2 binds a bio/medical AI repository audit to a machine-checkable memory contract, then demonstrates it on a real open-source bioinformatics repository.
When an AI Pipeline Passes — But One Path Still Must Be Held: EXP-034
EXP-034 tested whether a method-locked Bio-AI governance pipeline could survive modal expansion, AlphaFold EBI observer wiring, and AG-live measurement without breaking its PASS/BLOCK judgment baseline.
The Sheepwave Has a New Shape: OpenMythos and the Rise of Architecture Hype
A technical-opinion essay on OpenMythos, Claude Mythos, README-driven AI hype, and why architecture claims need source-level verification before becoming public belief.
OpenMythos v0.5.0 Code Review - Audit Report
OpenMythos collected thousands of GitHub stars and dominated AI discourse for a week. This is what happens when you actually read the code — and why the people who do always arrive too late to matter.