April 30, 2026 Karpathy's Wiki, OpenBrain, and Picking a Context Layer for AI Two memory models for AI work. One synthesises on write, one on query. Which to pick depends on whether you're a solo researcher or running multi-agent.
llmarchitecturetooling
Read article
April 28, 2026 Types of APIs and Event Queues: When To Use Each Four ways to move data between services. What each one buys you, where each one falls down, and when I reach for which.
architectureapirestgrpctrpcqueuesnodegopython
Read article
March 2, 2026 OpenVPN on an EC2 Bastion: Private Network Access Without the Complexity Setting up OpenVPN on a small EC2 instance as a bastion host for secure access to private AWS resources. No managed VPN service, no over-engineering.
awsarchitecture
Read article
Conversational AI: From RAG Prototypes to Domain-Specific SupervisionNovember 20, 2024 Per-Channel vs Per-User: What Memory Model Works for AI Chat Slack conversations are collaborative. Persisting context per channel captures the full picture. Per-user memory misses half the conversation.
llmarchitectureslack
Read article
Conversational AI: From RAG Prototypes to Domain-Specific SupervisionNovember 4, 2024 Building a Tool Builder: Making AI Tools Configurable Without Code The first API had hardcoded tools. The Slack bot needed different tools. I built a tool system where admins create, configure, and monitor tools from a dashboard.
llmtoolingarchitecture
Read article