Deep Dive
Durable State for Long-Running LLM Coding Sessions
A practical workflow for separating planning from execution, checkpointing progress in GitHub issues, and resuming multi-phase LLM implementation without context collapse.
Blog
10 posts
Deep Dive
From Chat to Agents: Designing Goal-to-Result Systems for Real Work
Why teams get more leverage from agent systems than chat interfaces, and the minimum architecture required to make agents reliable.
Deep Dive
How Paperclip Is Redefining AI Agent Orchestration for the Zero-Human Company
A practical look at Paperclip's model for running teams of AI agents around business goals instead of individual tasks, and why that changes the operating model of software and services.
Deep Dive
Why Long-Running AI Coding Sessions Fail
A practical control plane for keeping AI coding sessions on track: separate planning from execution, validate deterministically, reset context aggressively, and isolate parallel work.
Deep Dive
Open Database + Vector Stack: A Practical 2026 Baseline
A deep dive into choosing a modern open database stack with vector capabilities and clear operational tradeoffs.
Short Note
Vector Search on GPU Databases
A DBA-friendly explanation of how vector search works, why GPUs help, and where vector retrieval fits inside modern database and AI systems.
Short Note
How a 10 Billion Row SQL Query Runs in 200ms on a GPU Database
A DBA-friendly walkthrough of how modern GPU databases execute large analytical SQL queries using columnar storage, parallel scans, and GPU aggregation.
Short Note
Why Databases Are Moving Toward GPU Execution Engines
A practical, DBA-friendly explanation of why modern analytical databases are increasingly using GPUs for scans, joins, aggregations, and AI-adjacent workloads.
Short Note
SIMD vs SIMT Explained for Database Engineers
A DBA-friendly explanation of SIMD and SIMT using query execution, vectorized processing, and GPU mental models instead of hardware jargon.
Short Note
CPU vs GPU vs TPU Explained for Database Engineers
A practical, DBA-friendly guide to understanding CPU, GPU, and TPU architectures using database mental models instead of hardware jargon.