Projects
Building an ethics tool inside the tab people already use
AI Ethics Coach is a Chrome MV3 extension that reviews selected text and returns practical flags without pretending to replace policy or judgment.
Read →Blog
This page is for long-form writing. If you want quick weekly motion, use Timeline. If you want stable build records, use Portfolio.
Projects
Captain Whiskers: a trading agent that optimizes portfolios with a quantum circuit and signs them with post-quantum crypto
A hackathon build that had no business working: an autonomous on-chain trading agent fusing variational-quantum portfolio optimization, on-chain identity, a risk router, Gemini-driven signals, post-quantum signatures, and an eleven-node Byzantine-fault-tolerant verification layer. Here is the architecture, the math, and which parts were real versus theater.
Read →Projects
Auditing a multi-terabyte filesystem without melting the laptop that audits it
disk-archival-toolkit streams multi-million-row filesystem inventories, classifies storage tiers, and emits budget-aware archival manifests, all in bounded memory. A short note on why the streaming constraint is the whole design, not a detail.
Read →Projects
Making retrieval stop lying: agentic RAG for legal and property diligence
An agentic retrieval-augmented pipeline (LangGraph + Qdrant, served on vLLM, tuned for AMD MI300X) for India real-estate and M&A document review. Most 'AI for legal' demos fail at the same place: the retrieval quietly returns the wrong clause and the model confidently summarizes it. This is how I fought that.
Read →Projects
The NCAA model improved after I split the problem into seed zones
A practical update on tiered seed-band modeling, routing logic, and assignment optimization for NCAA seed prediction.
Read →Research
What the L1 cache is really doing to your finance kernels
An empirical cache-characterization study of four quantitative-finance kernels (Cholesky, Monte Carlo, GARCH, GEMM) on AMD EPYC, measured with PAPI on BigRed200. Written like a short paper, with the plots that did not flatter me included.
Read →Research
Quantum computing is linear algebra wearing a lab coat
Notes from Prof. Hong's lab on the matrix algebra under qubits, gates, entanglement, and measurement, and the one place it matters most for me: the quadratic speedup quantum amplitude estimation promises over classical Monte Carlo for derivatives pricing.
Read →Research
RegimeFactorZoo, part two: the replication actually works
A results post. I rebuilt the Fama-French three factors from raw CRSP and Compustat and matched Ken French's published series to 0.98/0.97, then asked whether the risk is actually priced (Fama-MacBeth) and whether individual characteristics predict returns (a nine-signal factor zoo). Numbers included, including the one with the wrong sign.
Read →Research
Do sparse factors survive a regime change?
RegimeFactorZoo replicates Fama-French and ML factor models on fully public data, then asks the question the factor zoo usually dodges: when you split the market by volatility regime, do the factors a sparse model selects stay selected? A short paper on the build, the math, and the WRDS rug-pull that made it better.
Read →