I gave AI agents a harm budget instead of trust and ran 19 experiments

Hi! I am Ricardo Sueiras, leading SDLC transformation at Indicium AI. That means I get to work with...

Budget alerts report the overrun after the money is gone. Here's a pre-flight, atomic budget cap for OpenAI and Anthropic clients that you can copy and paste.

Each of your 20 agents checked the budget and passed, and together they still overspent. Here's a thread-safe pre-flight cap in Python, plus what alerts miss.

A free coding agent fails in a predictable direction: it says yes. Ask for a one-line fix and the...

A viral rant says run your own LLM proxy; the HN thread asks how. Here is the runnable answer — one file, no API key — and the verbatim capture: the machine inventory your client volunteers, the retry your app never mentions, and the conve…

chore, feature, deep: three model and effort presets for Claude Code and Codex, plus the two settings that quietly override them.

My tab extension now names tab groups with AI for everyone: Chrome's built-in model when there is one, otherwise a tiny shared Cloudflare Worker on a free tier that stops instead of billing me.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...

This week I've been struggling with some kind of illness. My throat was dry and I couldn't breathe on...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle Watch the...