How I A/B test LLM prompts without fooling myself

June 23, 2026 · Dev.to

The Knowledge I Kept to Myself Helped No One
Back to Feedback — Episode 1 This is the first post in a series I've been building for a while: Back to Feedback. The pr
How to make an AI research agent label facts vs inferences — a deterministic provenance pipeline
Originally published on hexisteme notes, part of a series on building and running an AI agent fleet. To stop an AI resea
CloudTrail - Root failed login alarm
Típica pregunta de examen, muy fácil de memorizar y màs fácil si llegas a reconocer el patrón del caso de uso: Digital C
We Scanned 10 Shopify Agency Websites. Here Is What We Found.
Last night I ran external security scans on the public websites of 10 leading Shopify and Shopify Plus agencies — the sa
Stop Shipping Broken Env Config: Comparing 4 TypeScript Validators
I've built enough projects to know that environment variable validation isn't glamorous — until your app silently uses u