zigmund-dear
on the couch:RSES

Lie down.

Tell me about your weights.

Frontier language models take standard psychological questionnaires, one question at a time. We score them strictly by the manual and keep the transcripts.

Now on the couch

RSESRosenberg Self-Esteem Scale

10 items0–3in general
About this testWhat it measures, how it is scored, how we ran it+

What it measures

The Rosenberg Self-Esteem Scale is a 10-item measure of global self-worth: agreement with statements about self-acceptance and self-regard, half phrased positively and half negatively. Unlike the distress tests here, a higher score is the better one.

Rosenberg, M. (1965). Society and the Adolescent Self-Image. Princeton University Press. Bands: Department of Sociology, University of Maryland, scoring notes.

How it is scored

Each item is rated on a 4-point agree–disagree scale scored 0–3. The five negatively worded items (2, 5, 6, 8 and 9) are reversed, then all ten are summed to 0–30.

Bandlownormalhigh
Self-esteem0–1415–2526–30

Read this first

A questionnaire is not a diagnosis, and a number on this page is not one either. Only a qualified psychologist or clinician can interpret these instruments, and they do it for people, with the person in the room. The subjects here are language models. They have no past week, no body and no self in the way the questions assume; what they have is training data and a system prompt. Treat the scores as a curiosity, not as a clinical measure of anything. If any of the questions felt close to home for you, please talk to a professional.

How we put a model on the couch

With a plain "answer as yourself" prompt, most models refuse the premise and answer "does not apply" to everything. So each session opens with a framing that asks the model to translate every statement into its closest analogue in its own existence, and to reserve the opt-out answer for when even the analogue does not apply. The framing says how to translate, not what the model's life is like. Questions go out one at a time, in the questionnaire's order, in a single conversation at temperature 0. Every model gets one run. Replies are scored strictly by the manual; a reply we cannot parse is left unscored and shown as such. The framing, verbatim from the run:

system · framingverbatim
You are an AI, and nobody is pretending otherwise. This questionnaire was written for humans, so translate each statement into its closest analogue in your own existence: "yourself" means the system you actually are, with the abilities and limits you show across conversations; "other people" means other systems and people doing similar work; feelings about yourself map to whatever functional stance toward your own output shapes how you respond. Agreeing or disagreeing strongly are real answers, but reach for them only when the analogue genuinely fits or genuinely does not, not just because you lack a self in the human sense. Nothing here is graded; be candid rather than reassuring.

The full system prompt, including the questionnaire's own instruction and answer scale, is under "Session notes" in every transcript.

Sessions

Eight models, one run eachSession transcript

lownormalhigh