<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Connor Faulkner</title><description>Research, writing, and technical notes.</description><link>https://connorfaulkner.com/</link><item><title>Building cviz: A Spatial Map of Your Codebase</title><link>https://connorfaulkner.com/blog/building-cviz/</link><guid isPermaLink="true">https://connorfaulkner.com/blog/building-cviz/</guid><description>I built a native Rust tool that turns git repositories into interactive 2.5D spatial maps — and hooks into Claude Code to light up files in real time as the agent navigates.</description><pubDate>Sun, 29 Mar 2026 00:00:00 GMT</pubDate></item><item><title>What I&apos;ve Been Building</title><link>https://connorfaulkner.com/blog/what-ive-been-building/</link><guid isPermaLink="true">https://connorfaulkner.com/blog/what-ive-been-building/</guid><description>A snapshot of what&apos;s been occupying the late nights — physics simulations, LLM compression, telescope anomaly detection, a codebase visualizer, a crypto trading system, and a GPS football tracker.</description><pubDate>Sun, 29 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Building DjangoShip with Claude</title><link>https://connorfaulkner.com/blog/building-djangoship/</link><guid isPermaLink="true">https://connorfaulkner.com/blog/building-djangoship/</guid><description>I extracted the reusable parts of a Django job board into a SaaS boilerplate for European developers. Here&apos;s what that process actually looked like.</description><pubDate>Thu, 26 Mar 2026 00:00:00 GMT</pubDate></item><item><title>XGBoost Signal Confidence Filter for Algorithmic Trading</title><link>https://connorfaulkner.com/research/trading-bot/</link><guid isPermaLink="true">https://connorfaulkner.com/research/trading-bot/</guid><description>An XGBoost classifier trained on 3,033 historical signal outcomes that doubles win rate in a live crypto trading system — from 24% to ~50% — by scoring each signal&apos;s confidence before execution. Deployed in dry-run with three parallel strategies and a delta-neutral carry layer.</description><pubDate>Tue, 24 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Physics-Inspired LLM Optimization: 5 Directions, 9 Experiments</title><link>https://connorfaulkner.com/research/physics-llm/</link><guid isPermaLink="true">https://connorfaulkner.com/research/physics-llm/</guid><description>Testing whether structures from physics — thermodynamics, renormalization group, lattice theory, and mean-field dynamics — can guide LLM compression. Five research directions validated on GPT-2 124M: entropy-based quantization (2.6× better than uniform), RG-guided pruning, lattice attention with a phase transition, GPTQ interaction analysis, and metastable cluster verification.</description><pubDate>Fri, 20 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Anomaly Detection in SDSS Stellar Spectra</title><link>https://connorfaulkner.com/research/sdss-spectral-anomalies/</link><guid isPermaLink="true">https://connorfaulkner.com/research/sdss-spectral-anomalies/</guid><description>Seven anomaly detectors — from Isolation Forest to a conditional normalizing flow — running on public SDSS DR18 stellar spectra. Includes a physics-motivated PBH candidate screening pipeline, semi-synthetic evaluation harness, and a Streamlit dashboard. Scales to 50K+ spectra.</description><pubDate>Wed, 18 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Physics-Inspired k-Means Quantization for LLM Weights</title><link>https://connorfaulkner.com/research/spin-quant/</link><guid isPermaLink="true">https://connorfaulkner.com/research/spin-quant/</guid><description>26 experiments compressing GPT-2 with physics-motivated k-means codebook quantization. Best result: PPL=84.2 at 0.836 bits per weight — 38× compression vs FP32. Null results triangulate the GPTQ design from first principles.</description><pubDate>Thu, 12 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Building ising-rs: From Python Script to GPU-Accelerated Research Platform</title><link>https://connorfaulkner.com/blog/building-ising-rs/</link><guid isPermaLink="true">https://connorfaulkner.com/blog/building-ising-rs/</guid><description>The journey from a college Python script to a publication-grade Monte Carlo engine achieving 0.01% accuracy on the 3D critical temperature.</description><pubDate>Mon, 09 Mar 2026 00:00:00 GMT</pubDate></item><item><title>DNS Threat Intelligence: Detecting DGA Families in the Wild</title><link>https://connorfaulkner.com/blog/dns-threat-intelligence/</link><guid isPermaLink="true">https://connorfaulkner.com/blog/dns-threat-intelligence/</guid><description>Technical notes on detecting domain generation algorithms through DNS traffic analysis — expanding on published research at Akamai.</description><pubDate>Mon, 09 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Hello World</title><link>https://connorfaulkner.com/blog/hello-world/</link><guid isPermaLink="true">https://connorfaulkner.com/blog/hello-world/</guid><description>First post — what this blog is for and what to expect.</description><pubDate>Mon, 09 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Ising Model Simulation in Rust + WebAssembly</title><link>https://connorfaulkner.com/research/ising-rs/</link><guid isPermaLink="true">https://connorfaulkner.com/research/ising-rs/</guid><description>A publication-grade Monte Carlo simulation engine for classical spin models, achieving 0.01% accuracy on the 3D critical temperature. Supports three universality classes, GPU acceleration via CUDA, and finite-size scaling analysis — targeting Physical Review E.</description><pubDate>Fri, 06 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Phishing Campaigns Targeting USPS See as Much Web Traffic as the USPS Itself</title><link>https://www.akamai.com/blog/security-research/phishing-usps-malicious-domains-traffic-equal-to-legitimate-traffic</link><guid isPermaLink="true">https://www.akamai.com/blog/security-research/phishing-usps-malicious-domains-traffic-equal-to-legitimate-traffic</guid><description>Akamai threat-research writing on USPS-targeted phishing infrastructure and the scale of malicious traffic reaching it.</description><pubDate>Thu, 25 Apr 2024 00:00:00 GMT</pubDate></item><item><title>Deep Analysis of Hospitality Phishing Campaign Shows Global Threat</title><link>https://www.akamai.com/blog/security-research/hospitality-phishing-campaign-dns-analysis-global-threat</link><guid isPermaLink="true">https://www.akamai.com/blog/security-research/hospitality-phishing-campaign-dns-analysis-global-threat</guid><description>A coauthored Akamai investigation into a hospitality-focused phishing campaign, with emphasis on DNS analysis and its broader global impact.</description><pubDate>Thu, 19 Oct 2023 00:00:00 GMT</pubDate></item><item><title>DGA Families with Dynamic Seeds: Unexpected Behavior in DNS Traffic</title><link>https://www.akamai.com/blog/security-research/dga-dynamic-unexpected-behavior-in-dns</link><guid isPermaLink="true">https://www.akamai.com/blog/security-research/dga-dynamic-unexpected-behavior-in-dns</guid><description>Akamai security research on DGA families that use dynamic seeds, focused on how that behavior appears in DNS traffic and why it matters for detection.</description><pubDate>Wed, 06 Sep 2023 00:00:00 GMT</pubDate></item><item><title>Genetic Substructure Analysis via PCA</title><link>https://connorfaulkner.com/research/genomics-pca/</link><guid isPermaLink="true">https://connorfaulkner.com/research/genomics-pca/</guid><description>Analysis of genetic substructure across global populations using genome-wide SNPs and principal component analysis on the 1000 Genomes Project dataset.</description><pubDate>Sat, 01 May 2021 00:00:00 GMT</pubDate></item></channel></rss>