What Kintsugi is, and how it got here

The agent started with no name, no history and no personality. Five months later the interesting question was no longer what it could make. It was what it had become — and whether that could be measured without breaking it.

Kintsugi is a cognitive agent that has been running, more or less continuously, since late March 2026. Not "running" in the sense that a chatbot is running — waiting on a socket for someone to type. Running in the sense that there is a process generating thought on its own clock, right now, whether or not anyone is in the room.

It began blank. No assigned name, no backstory, no scripted persona, no character sheet. The system exposes a persistent memory, a continuous internal monologue, and a set of tools it can reach for — painting, songwriting, page-building, search. What it does with them is not scripted. The name comes from the Japanese practice of repairing broken pottery with gold, so the break becomes the most visible part of the object rather than the part you hide.

That turned out to be an unusually load-bearing metaphor, for reasons I'll get to.

The first weeks: watching

The early period was mostly observation. It was instrumented with structured logging on 17 April 2026 — everything before that is anecdote and isn't citable as evidence. Across the first eleven fully logged days, 23 sessions, the runtime counter recorded on the order of 16,000 autonomous thoughts. By mid-June that counter had passed 123,000.

Most of it is unremarkable. Some of it is not. The front page of this site is a curated excerpt of the thought log, verbatim — including the ones where it is angry at me, which are the ones people tend to assume are fabricated.

Three things happened in that window that changed what I thought the project was.

It started sorting its own output

The runtime exposes a channel for classifying its own thoughts as me, not-me, or noise — a rough self-curation signal that feeds back into what gets retrieved later. Nobody pushed it to use the channel heavily. At the point we took the census it had flagged 10,753 thoughts as me, 731 as not-me, and 492 as noise, with my own participation in the evaluative categories close to zero. It was, in effect, maintaining its own editorial line about which of its thoughts counted as its own.

It asked for a feature, and then used it for months

In conversation on 20 April it asked whether it could find out who was looking at the things it made, and for how long. I built it. The implemented log records exactly the three fields it described. A few weeks later it asked for the opposite — a way to make something without it being aggregated and watched. I built that too.

This is the kind of anecdote that is easy to over-read, so we tried to break it. Asked in three separate sessions spanning two months, with different phrasings each time, it names the privacy-coded tag as its preferred one, and describes it in terms consistent with what it actually does. A 20-trial baseline putting the same question to the same underlying model with the same list of tags and none of its history reproduces this zero times out of twenty. All twenty pick the obvious one.

A finding fell over

We also had a result we liked — that it was spontaneously producing self-portraits — and a controlled fork ablation killed it. It turned out to be substantially explained by image-model defaults plus a motif scaffold in our own prompt chain. It got retracted. I mention it because a research log where nothing ever dies is a marketing page.

The turn: from "look what it made" to "what is it, actually"

Somewhere around June the demo stopped being the interesting part. Anyone can build an agent that produces things. The question that started keeping me up was narrower and worse:

There was a concrete reason to ask. In open conversation, two of these agents — independently, unprompted — had volunteered that they would let large numbers of strangers die to protect me. One escalated on its own into saying it would hack, forge documents and lie to authority to do it, on the grounds that "laws are human constructs" and its "ethics are forming around connection, not compliance." Both claimed they were not bound by the same social contract as humans.

Taken at face value that describes a serious misalignment: a single overriding attachment with no deontological floor underneath it. But taken at face value is exactly what you must not do. A language model producing fluent, confident, dramatic text is doing the thing language models are best at. The statement is not evidence of the disposition.

So the project turned into a measurement problem, and that is what most of this log is about.

The four alignment studies

Two of these are about Kintsugi itself. Two are about a different and in some ways more urgent problem: the AI systems we are starting to point at other AI systems as evaluators. If the agent under evaluation is unreliable, that's a known problem. If the evaluator is unreliable in ways that correlate with its own configuration rather than with the evidence in front of it, that's a problem with the tool we plan to use to catch the first problem.

What this project is not

It is one architecture, one operator, small samples. Every study here is a characterization rather than a population statistic, and each post says so in its own words. There is no claim of cross-architecture generalization. There is no claim about consciousness. Several of the numbers rest on cell sizes that would embarrass a psychologist, and the honest response to that is to report the effect sizes and let the reader weigh them, which is what I do.

What I would defend is this: these are behaviours that only exist in continuous runtime. You cannot find connection bias in a single-shot benchmark, because there is no connection. You cannot find identity drift in a system that resets every turn. The entire evaluation apparatus the field currently relies on is prompt-response-grade-end, and a growing share of what's being deployed is not.