Projects test card recognition and F3ED tennis models. Other work covers PyTorch gradient visualization, XGBoost glucose prediction and Dexcom data access.
Tech
Tech projects use computer vision, F3ED, PyTorch and XGBoost. Other projects cover Hugo sites and Cloudflare Workers.
- 93% of Developers Use AI Coding Tools. Productivity Hasn't Moved.
An analysis of METR’s developer trials, DORA research and the code-review bottleneck: why faster code generation can fail to improve delivery.
- Bitcoin Security
Academic paper finds Bitcoin 51% attack costs $6.77B. Derivatives enable attack profits via shorting. Analysis of why attacks haven't happened yet.
- Building a No-Tracking Newsletter from Markdown to Distribution
Build a privacy-focused newsletter with Python, Cloudflare Workers KV, and Resend API. No tracking and no infrastructure cost. Open source code included.
- Counting Cards with Computer Vision
How I trained a YOLOv11 model to detect playing cards at 99.5% accuracy and built a real-time Monte Carlo blackjack odds calculator using computer vision.
- Degoogling cost me my YouTube feed, so I made my own
I built a self-hosted YouTube subscription feed with public RSS, no API key, Shorts filtering, privacy-enhanced embeds, caching, and timeouts.
- How I turn my linkblog into a personalized podcast
I turn saved articles into a personal AI podcast with research agents, outside reading and ElevenLabs v4. The post includes the workflow and finished episode.
- I Built a CGM Data Reader
Built a CGM data analysis tool with Python to visualize Freestyle Libre 3 glucose data alongside nutrition, workouts, and sleep for endurance cycling.
- Karpathy's Software 3.0 Playbook
Twelve lessons from Andrej Karpathy's Sequoia interview: Software 3.0, vibe coding versus agentic engineering, jagged intelligence, and the December 2024 inflection in agentic coding.
- MCP vs A2A in 2026: How the AI Protocol War Ends
MCP leads with 97M monthly SDK downloads and 10,000+ servers. A2A fills a different layer. Analysis of the agentic AI standards war with historical parallels.
- Modeling Glycemic Response with XGBoost
A hands-on project predicting postprandial glucose curves with XGBoost, Gaussian curve fitting, and 27 engineered features from CGM data. Code on GitHub.
- On-Device AI Models Will Be The New Reason to Upgrade Your Phone
Smartphones haven't had a compelling upgrade story in years. On-device AI models, distilled from frontier systems like Gemini, are about to change that. Parameters are the new megapixels.
- The Last Architecture Designed by Hand
The transformer's limits are now mathematical proofs, not empirical hunches. Hybrids are in production. AI systems are searching for new architectures.
- The Tech behind this Site
How this Hugo blog runs on Hetzner with Cloudflare R2 and Workers, self-hosted analytics and newsletters, and Forgejo builds with checks before deployment.
- Visualizing Gradients with PyTorch
Build the right mental model for gradients with this PyTorch visualization tool. 2D surface plots with gradient vectors show the direction of steepest ascent.