akaOSS

Research

Findings

Case-study write-ups produced by running the kits — each one a reproducible experiment with checked-in runs, scored by humans, not LLMs.

The paper

An AI Measurement Problem

perspective paper·the argument this feed measures

The AI failure crisis is at root a measurement crisis. The paper synthesizes benchmark science, cognitive neuroscience, uncertainty quantification, and enterprise deployment data to argue for Assist-Not-Complete: evaluate AI on whether it assists humans without displacing them, not on whether it can finish the task alone.

The gate is the unit of measurement

2026-07-21·essay

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.

gateshuman-in-the-loopeval-kitHITL KitEU AI ActmeasurementAssist-Not-Complete

The credibility stack: what a stranger checks before trusting your package

2026-07-18·essay

Before anyone reads your test suite, they run an implicit checklist: does the published package install, do the README examples compile, does the API change without warning. We built those checks as CI harnesses across three of our packages and ran them on ourselves. First run: one package shipped no type declarations at all, and three README examples had never compiled.

testingpublish smokeREADME-runsAPI surfaceeval-kitHITL Kittag-kit

Watching the agent work: observability for agent-driven asset pipelines

2026-07-18·essay

When an AI coding agent became a real part of a Blender → glTF game pipeline — writing the export scripts, running them, rearranging the shipped files — the speed-up came with a blind spot: no picture of what it was actually doing. Hologram is the pattern that closed the gap: one append-only event log, a live dashboard beside the assets, and the same pipeline handed back to the agent as a small non-destructive MCP surface.

HologramMCPBlenderglTFobservabilityread-only by design

An instrument, not a judge: why humans score the agents

2026-07-18·essay

LLM-as-judge shares the blind spots of the agent it grades — both were trained against similar objectives, so the judge rationalizes the same failures. eval-kit's answer is a measurement instrument built around step-level human judgment: per-step tool-match assertions, distractor tasks that score the refusal, and a five-dimension 0–3 rubric the judge never touches by default.

eval-kitLLM-as-judge5-dim rubricdistractor taskstool_matchAssist-Not-Complete

Welcome to the lab log: what this feed measures, and how

2026-07-18·finding

Findings here are produced by running eval-kit suites, displayed with HITL Kit components, and scored by humans on a five-dimension rubric — never by an LLM judge. Every entry links its experiment folder and checked-in run JSON, and none of it is leaderboard material.

Assist-Not-Complete5-dim rubricdistractor taskseval-kitHITL Kittag-kit