Last month, curl paused security reports for a stretch because the queue had filled with AI-generated...
I Built an LLM Filter That Prefers Silence Over Slop — and the Eval Harness That Keeps It Honest
Related
The Prompt Quality Report: What 1,000 Scored Prompts Reveal
We scored over 1,000 real prompts (average 52/100). Original data on what separates a good prompt from a bad one.
Routing Down Is Easy. Knowing When Not To Is Hard: Why Cheap Models Break Your Coding Agent
Disclosure: I maintain Lynkr, an open-source router whose design decisions this post explains. The...
Memory Engineering Is a Promotion Pipeline, Not a Pile of Notes
A lot of AI memory systems start with the same temptation: "Just save the useful thing." That...