TL;DR: Our LLM-as-judge agreement (Cohen's kappa against human labels) swung between 0.41 and 0.63...
More eval traces will not stabilize your kappa. Stratify the ones you have
Related
When Everyone Has AI Agents, Who Knows What They’re Doing?
We started building OliverGraph to give teams and their AI agents shared context across GitHub,...
🐾 PawSafe: An AI-Powered Food Safety Checker for Dogs
This is a submission for Weekend Challenge: Dog Days Edition What I Built PawSafe is an...
One terminal, two trust levels — running Claude Code against a real subscription and a cheap proxy
A working supervisor/executor split for Claude Code, one command for the real subscription and one for a proxy-routed cheap tier, and why they're deliberately asymmetric.