akaOSS
Open source · by akaieuan

Open-source software for human-in-the-loop AI.

Five projects: a measurement family for AI that assists without displacing — components, evals, annotation — and tooling for the agents that build alongside you.

The thesis

Human-in-the-loop AI, measured properly.

Evaluate AI on whether it assists humans without displacing them — not on whether it can finish the task alone.

Read the paper: An AI Measurement Problem
Latest from the lab

The gate is the unit of measurement

№ 005·published

A reframing of what the akaOSS measurement family actually measures: not task completion, but the gate, the moment an agent hands control back to a human. Gates come in two kinds that must never share a metric, autonomous benchmarks structurally penalize both, and a gate over unverifiable output is oversight theater. Regulation now mandates effective human oversight; nothing measures whether oversight is effective. That gap is the research program.

All findings