Are We Looking at Model Behavior Too Narrowly?

IntroductionResearch on AI systems’ behavior frequently focuses on predefined behavioral targets, such as sycophancy, deception, or reward hacking. While useful, it is unclear how far progress on individual targets translates into understanding (and later improving) models’ overall behavior. In this post, I argue that two gaps make this difficult to assess: we lack a principled measure of how far findings on individual targets generalize, and recent work (Pawar et al., 2026; Liu et al., 2026) suggests that training on one value can affect others in ways that are hard to predict. I then review methods that do not require specifying targets beforehand, particularly model diffing, and propose directions I consider promising, drawing on my early pilot experiments. BackgroundA common approach to studying AI systems’ behavior (Sharkey et al. 2023) is to focus on predefined behavioral targets, i.e., properties or patterns researchers define with respect to the models’ (context, output) pairs. They include desirable properties such as honesty, helpfulness, and harmlessness, and undesirable ones such as sycophancy, deception, and reward hacking. However, this approach has several limitations. Chughtai, Engels and Nanda (2026) highlight one of them when motivating their experiments: “Standard methods for assessing the safety and capabilities of frontier state-of-the-art LLMs rely on capability and propensity evaluations. This evaluation-driven paradigm has had reasonable success, but has a fundamental limitation - it can only expose things that you are looking for, which you know how to measure.” I argue that being limited by the behaviors we can identify and specify beforehand does not necessarily undermine the usefulness of this approach, as long as progress on individual behavioral targets compounds into meaningful progress toward understanding and improving models' overall behavior. The question is whether this is actually the case. Behavior, propensity and behavioral spa