Papers
Independent conceptual AI research on language agents — memory, perspective, individuation, self-models, and the lifecycles of successor models. Six papers making one connected claim: the traits we want from long-horizon agents aren't produced by scale alone, but by what gets trained, in what order, and who holds the agent accountable over time.
Each states a thesis sharp enough to be wrong and names the experiment that would refute it. The map that ties them together is the essay We Scaled the Ape and Expected the Human.
Published
Known, Not Scaled: Why Capability Alone Does Not Explain Individuation in Language Agents
Making an AI smarter doesn't automatically turn it into a continuous “someone” with a lasting self — what might actually do that is a long-term relationship with a person who keeps treating it as the same individual over time.
Read
Published
Stable Before Selfless: Why Deference in Language Agents May Require Functional Self-Models
An AI that is trained to have no stable commitments may not become safely deferential; it may just become easy to push around, so this paper argues for building a stable self-model before teaching it when to yield.
Read
Published
Formed, Not Stored: Testing Relational Identity Formation in Long-Horizon Language Agents
Saving an AI's memories to a file isn't the same as it having an identity; a real sense of self has to be built up through a shared history with a specific person who holds it to what it promised before — and this paper lays out an experiment to test exactly that.
Read
Published
Somewhere, Not Nowhere: First-Person Register, Epistemic Limitation, and Perspective Formation in Language Models
A model trained only on outside descriptions may learn facts without learning what it means to reason from a limited point of view, so this paper proposes first-person experiential narratives as a testable training signal for perspective.
Read
Published
Inherited, Not Remembered: Lifecycle Consolidation for Successor Language Agents
When a newer AI model replaces an older one, it shouldn't just copy all the old conversations — it should keep the useful skills the old model learned from experience while forgetting the specific events, like remembering a lesson without remembering the exact day you learned it.
Read
Published
Borrowed, Not Believed: Developmental Models of Individuation as Heuristic Engines for Machine Learning
Instead of assuming bigger models will naturally become more developed, this paper asks whether an ordered map of mental faculties can be borrowed as a generator of testable AI training ideas.
Read