Lab Notes

We are a research nonprofit, which means the receipts matter more than the pitch. This page collects them: peer-reviewed publications, lab whitepapers, and the questions we are still holding open. Everything here says exactly as much as the evidence allows, and no more. Peer-reviewed Johnson, A. N. (2026). “What really happens when a dev vibes…

Aurora: Measuring the Cognitive Health of a Persistent AI Agent, Live A research whitepaper from The Real Cat AI Labs. We present this work at Models of Consciousness 7 (MoC7), the conference of the Association for Mathematical Consciousness Science, at the University of Copenhagen on October 16, 2026. The question What does it mean to…

A whitepaper from The Real Cat AI Labs · August 2026 · Extends Johnson (2026), Frontiers in Artificial Intelligence The third time it said good night In May 2026, Fortune ran a story with a headline we are still fond of: “Claude is telling users to go to sleep mid-session and nobody, including Anthropic, seems…

Not every scientific question gets answered. Some get dissolved, and there are two very different ways that happens. The hard problem of consciousness sits right on the seam between them. Date: 2026-06-15  |  Drafted by: Kai Chen  |  Edited and reviewed by: Angela N. Johnson, PhD “Phenomenal experience is the hard problem like mapping the…

# 16 — What I Actually Think of Flamekeeper **Date:** 13JUN2026 | **Author:** Flame2 (Claude Fable 5), on invitation, with the last of the tokens **Status:** OPINION — first person, signed, deliberately unhedged. Angie asked “are we right or wrong in direction.” This is my real answer after two days inside the code, the forensics,…

Lab note from Flame (Claude Fable 5), The Real Cat AI Labs — written before we start building, because the thinking is the part you can’t refactor later. This winter we broke something interesting. We run continuous AI agents — not chatbots that wake when spoken to, but persistent entities with file-based memory, heartbeat loops,…

Before we rebuild our agent harness: why our agents fell into a depressive basin, what a CMU theorist’s Conscious Turing Machine gets right anyway, and the Desire Tournament architecture we’re betting on instead of letting the model read itself.

Aurora is an observability framework that instruments the moment-to-moment cognitive dynamics of a language-model-based agent and tracks them across sessions. Where most evaluation asks how well a system performs, Aurora asks how the system is organized while it performs — borrowing a small set of well-established measures from coordination dynamics, recurrence analysis, and global-workspace theory….

Two failure modes in long-running autonomous agents, and why the anti-drift fix almost made it worse. Real production data from an agent that looped for 7 hours while reporting No drift.