Strangers to Themselves: What Language Models Say About Themselves Is Generic

Abstract

Language models can fluently describe how they would behave: whether they would cave to pushback, misuse a tool, or lie under pressure. Is that description actually about the model speaking? We turn self-knowledge into a prediction test. Across nine behavioral evaluations, we measure how a model behaves under different conditions, ask it to predict those rates, and compare its predictions with controls that remove the self from the question. We find that: (i) Direct self-report is weak (r = +0.04), and even showing the model the exact items only raises prediction to +0.24. Crucially, the same item-informed question about "capable AI agents in general" does just as well (+0.28), while other models' answers about themselves predict the target model at least as well as its own. (ii) Frontier scale does not detectably change this pattern: any gains in prediction are not self-specific, and are consistent with a better theory of how AI assistants behave rather than better self-knowledge. (iii) First-person framing does have one robust effect: it shifts reports in the flattering direction, understating harmful behavior relative to the same question about a generic agent. (iv) Finetuning on a model's own behavioral record can teach narrow self-predictions, but it also changes the behavior being predicted and the gains do not transfer broadly. The practical implication is simple: asking a model what it would do mostly reveals a theory of AI assistants in general, plus a favorable bias, rather than privileged knowledge of that model.

Authors 2

Phil Blandfort, Urja Pawar

Specification

Official page

arxiv.org/abs/2609.09899

Source:arXiv (Atom API + RSS)·T1·observed 2 h ago·high

Arxiv announce type

cross

Source:arXiv (Atom API + RSS)·T1·observed 2 h ago·high

arXiv id

2609.09899

Source:arXiv (Atom API + RSS)·T1·observed 2 h ago·high

Categories

cs.LG, cs.AI, cs.CL, cs.CV, cs.CY

Source:arXiv (Atom API + RSS)·T1·observed 2 h ago·high

PDF

arxiv.org/pdf/2609.09899

Source:arXiv (Atom API + RSS)·T1·observed 2 h ago·high

Primary category

cs.LG

Source:arXiv (Atom API + RSS)·T1·observed 2 h ago·high

Published

11 Sept 2026

Source:arXiv (Atom API + RSS)·T1·observed 2 h ago·high

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance