Writing Hub
AI governance essays, reasoning systems notes, experiment logs, and technical writing across BioAI and engineering practice.
Project Topics
The Repo Is Right There. Why Are You Checking Their CV?
In 2026, AI researchers and engineers use the same words to mean opposite things. This is not a communication problem. It is an incentive problem with a vocabulary leak and it's where most AI projects actually fail.
My LLM Kept Forgetting My Project. So I Built a Governance Schema.
Session loss isn't a UX inconvenience — it's a structural failure with compounding consequences for long-running AI projects. This post defines the problem precisely and introduces MICA, a governance schema for AI context management.
I Built an Ecosystem of 46 AI-Assisted Repos. Then I Realized It Might Be Eating Itself.
An ecosystem of 46 AI-assisted repos can become a closed loop. This article explores structural blind spots, self-validating toolchains, and the need for external validators to create intentional friction.
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.
Your Agentic Stack Has Two Layers. It Needs Three.
Most agentic stacks cover tools and skills, but miss intent governance. Learn why a third layer is needed to stop AI drift, scope creep, and technically correct systems heading in the wrong direction.
Why Reasoning Models Die in Production (and the Test Harness I Ship Now)
Why reasoning models fail after deployment, what production drift looks like, and the test harness I use to catch fragile logic before itships
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
Showing page 4 of 5 · 60 matching posts