AI Development Tools
-
Local LLM hardware requirements start with memory bandwidth
Local LLM hardware requirements for Ripple-65B, a 65B dense Apache 2.0 model: file sizes, KV cache and a speed ceiling per machine. I did the maths.
-
Graph engineering for agents: what a prompt chain forgets
Graph engineering models an agent system as nodes and edges, not a prompt chain. Here is the idea, five patterns, and how my open-source Yaaf uses it.
-
Kanzo is a one-developer kanban board for coding agents. One call cost 92k tokens.
I ran the Kanzo MCP server, a 4.9 MB kanban board for agents, through 92 task calls in five bursts: zero doubles. Then three things broke my trust.
-
Claude Code Reviews: 50% Productivity Gains vs. Rising Quality Control Concerns in Enterprise Development
Claude Code is doing two things at once. It is making developers faster, and it is making some teams nervous about what speed is doing to code quality.…