Writing Hub
AI governance essays, reasoning systems notes, experiment logs, and technical writing across BioAI and engineering practice.
Project Topics
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.
How do you know when your entire AI pipeline is wrong — not just one model? (EXP-033)
EXP-033 shows how to validate an entire AI pipeline, not just one model, using five-gate checkpoints, reproducible PASS/BLOCK parity, AlphaGenome on/off testing, and fully traceable governance decisions.
What an AI Reasoning Engine Built for Alzheimer's Metabolic Research: A Code Walkthrough
A code walkthrough of an AI reasoning engine for Alzheimer’s metabolic research, showing how literature ingestion, causal inference, and executable biomarker scaffolds generate falsifiable pre-validation hypotheses.
From Fail-Closed Blocking to Reproducible PASS/BLOCK Separation (EXP-032B)
A validation study showing how EXP-032B achieved reproducible PASS/BLOCK separation across A/B/C control arms by patching false-blocking causes, improving observability, and measuring replay drift under observer-shadow conditions.
Chaos Engineering for AI: Validating a Fail-Closed Pipeline with Fake Data and Math
A case study in AI governance showing how synthetic invalid inputs, structural disagreement, SIDRCE ethics checks, and end-to-end reliability scoring triggered a safe BLOCK verdict in a biomedical pipeline.
From 97% Model Accuracy to 74% Clinical Reliability: Building RSN-NNSL-GATE-001
Learn how RSN-NNSL-GATE-001 turns high model accuracy into system-level clinical reliability by blocking unsafe AI pipeline decisions, measuring end-to-end risk, and enforcing fail-closed governance.
When Adding Chai-1 and Boltz-2 Exposed Hidden Model Disagreement(Trinity Protocol Part)
See how adding Chai-1 and Boltz-2 to an AlphaFold workflow exposed hidden model disagreement, increased drift, and revealed why failed convergence can be the most valuable signal in computational biology.
Orchestrating AlphaFold 3 & 2 with Python: Handling AI Hallucinations using Adapter Patter (Trinity Protocol Part 1)
Learn how to orchestrate AlphaFold 3 and AlphaFold 2 with Python using the Adapter Pattern to detect AI hallucinations, measure structural drift, and improve protein prediction reliability.
I Integrated AlphaFolder3 & AlphaGenome. It Looked Perfect. Then It Failed the "Honesty Test."
A real-world experiment integrating AlphaFold3 and AlphaGenome revealed a critical lesson: AI predictions that look perfect can still fail the ‘honesty test.’ A deep dive into bioinformatics, model validation, and AI reliability in drug discovery.
How Failing in 2 Hours Saved 8 Months of Drug R&D: Engineering a "Truthful Null" with Upadacitinib
A bioinformatics case study on Upadacitinib showing how SR9 stability scoring and drift analysis exposed lipid carrier incompatibility early, saving months of drug delivery R&D
RExSyn Nexus 0.6.1 - Stop Hallucinating Proteins: How We Built a 7D Reasoning Engine with AlphaFold3
RExSyn Nexus 0.6.1 adds Structure as a 7th reasoning dimension, using AlphaFold3 confidence signals to reject biologically plausible but physically impossible protein hypotheses with deterministic, auditable validation.