I run a one-person "dark factory" of AI agents for $0.015 per task. Here is what broke.

The provider that failed was the feature: building a model-agnostic AI arbiter (Kimi K2 · Qwen · EIP-712)

I showed 30 AI models 336 monitoring dashboards. Most of them can't tell time.

20 Hacktoberfest Ideas That Wins You TheWeekend Challenge

DevOpsDays Vilnius 2026

Terraform Says Passing. The CIS Benchmark Says Critical. An Agent That Resolves Cloud Security Clashes via a Sanity Graph

CodeSage: Code Intelligence for AI Agents, and Why I Rebuilt Its Models

TruthGraph: the right rule depends on when—and for whom

My local AI agent remembered things I never said. A reader's security review found it.

How One "Generate Draft" Button Changed the Design of My Writing Tool

How I built session checklists in my AI assistant: plans the agent can't quietly rewrite