Some of the things I've been building.
Personal website and blog built with Next.js 16, static export, and a terminal/hacker aesthetic.
Scripts for bootstrapping a Mac mini cluster using Exo Labs clustering software.
Production-ready LiteLLM deployment with PII guardrails for infrastructure deployment.
A modern attempt at the original Perceptron experiment conducted by Frank Rosenblatt in 1957/1958.
A modern take on the Frank Rosenblatt perceptron experiment from 1958.
Thoughts on AI engineering, agents, and security.
The inverse of securing agents: building an agentic system that runs a traditional red-team engagement. Recon, enumeration, exploitation, and reporting as an agent loop, with scope enforcement and human gates as the core architecture.
An agent whose only memory is the context window restarts from near-zero every time it compacts. Here is how to give agents memory that lasts: working, episodic, and semantic memory, write-time fact extraction, and hybrid retrieval, plus the failure modes that break naive RAG-as-memory.
Anthropic's 'Building Effective Agents' draws a hard line between workflows and agents. Here is what each pattern - prompt chaining, routing, parallelization, orchestrator-workers, evaluator-optimizer - looks like in practice, and how to choose the simplest one that works.