Writing Hub
AI governance essays, reasoning systems notes, experiment logs, and technical writing across BioAI and engineering practice.
Project Topics
FLAMEHAVEN FileSearch: Why This RAG Engine Feels Different from the Usual Stack
A technical look at FLAMEHAVEN FileSearch: BM25+RRF hybrid retrieval, chunk-addressable indexing, deterministic DSP vectors, and the trade-offs behind a lower-overhead self-hosted RAG engine.
It Gets Smarter Every Scan: AI-SLOP Detector v3.5.0 and the Self-Calibration Loop
AI-built apps are starting to fail in public. Not every failure is static-analysis territory, but many share the same upstream condition: plausible-looking code passing review without carrying enough real logic. AI-SLOP Detector v3.5.0 adds a self-calibration loop to reduce that gap.
Can AI Review Physics? Yes — That Is Why We Built SPAR
SPAR is a deterministic framework for claim-aware review: checking whether an output deserves the claim attached to it.
Bridging the Gap: From AI Slop to Mathematical Governance
A mathematical framework for detecting AI-generated code slop using AST distributions, Jensen-Shannon divergence, and geometric governance gates.
My AI Maintainer Kept Making Wrong Calls. So I Made It Report Its State Before Touching Anything.
Part 6 moves from landscape to operation. This is what MICA looks like when it is actually running inside a real maintenance workflow — session report, self-test, drift, invariants, and operator judgment.
Prompt → RAG → MCP → Agent → Harness, and What?
Why the next layer in AI may be governance infrastructure, not just better agents.
The Harness Is the Product: What the Claude Code Leak Actually Revealed About AI Agent Architecture
The Claude Code leak exposed more than source. It revealed that modern AI agent performance depends heavily on the harness around the model.
After Auditing 10 Bio-AI Repositories, I Think We're Scaling the Wrong Layer
After auditing 10 open-source Bio-AI repositories, one pattern stood out: the field is scaling packaging faster than verification. Here is what that gap actually costs.
I Audited 10 Open-Source Bio-AI Repos. Most Could Produce Outputs. Few Could Establish Trust.
I audited 10 visible repositories. Most could produce outputs. Very few could establish what those outputs meant.
Everyone Was Talking About Context Engineering. Nobody Had Solved Governance.
Everyone Was Talking About Context Engineering. Nobody Had Solved Governance.
Bio-AI Repository Audit 2026: A Technical Report on 10 Open-Source Systems
We audited 10 prominent open-source Bio-AI repositories using code inspection and STEM-AI trust scoring. 8 of 10 scored T0: trust not established. Here is what the code actually shows.
The Model Already Read the README. MICA v0.1.8 Made It a Protocol
v0.1.7 made scoring a contract with fail-closed gates. v0.1.8 recognized that README-first behavior could serve as invocation — and formalized it as a schema-level protocol. This article uses simplified examples to show how the invocation gap that had existed since v0.0.1 was finally closed
Showing page 2 of 5 · 56 matching posts