When AI Gets the Tickets Right but the Totals Wrong

Same 60 questions, same prompt, same grader. Only reasoning_effort changes. 1,800 graded calls later: one real accuracy gain, many bigger bills, and a model that counted two tools as 10,016.

This is a submission for the Kaggle Benchmarking Challenge. 🎥 3-minute overview (narrated): ...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked Every...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

Kagaz (कागज़, "paper") is an offline-first tool that generates printable bilingual Hindi and English...

Most agent skills frameworks are just text prompts in markdown files, then I found an open source...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

I didn't set out to "replace my workflow with AI." I set out to answer a narrower, more honest...

One free, MIT-licensed MCP server: SEC filings, markets, options, the Fed, macro data, quant analytics and backtest validation behind three tools. What it does, how it compares, and the bugs we caught on the way.