Alex Mallen

This is a brief elaboration on The behavioral selection model for predicting AI motivations, based on some feedback and thoughts I’ve had since publishing. Written quickly in a personal capacity. The main focus of this post is clarifying the basic machinery of the behavioral selection model, and conveying why it...

Previously, we proposed spillway motivations as a way to mitigate misalignment induced via training a model using flawed reward signals. In this post, we present some early-stage empirical results showing how spillway motivations can be used to mitigate test-time reward hacking even if it is reinforced during RL. We compare...

Current AIs routinely take unintended actions to score well on tasks: hardcoding test cases, training on the test set, downplaying issues, etc. This misalignment is still somewhat incoherent, but it increasingly resembles what I call "fitness-seeking"—a family of misaligned motivations centered on performing well in training and evaluations (e.g., reward-seeking)....

TL;DR We test to what extent Qwen3-32B behaves as though it is trying to predict what "Qwen3" would do. We do this by using Synthetic Document Finetuning (SDF) to instill meta-beliefs of the form "Qwen3 believes X, even though X is false", then check whether the model acts as though...

We’d like to use powerful AIs to answer questions that may take a long time to resolve. But if a model only cares about performing well in ways that are verifiable shortly after answering (e.g., a myopic fitness seeker), it may be difficult to get useful work from it on...

It's plausible that flawed RL processes will select for misaligned AI motivations.[1] Some misaligned motivations are much more dangerous than others. So, developers should plausibly aim to control which kind of misaligned motivations emerge in this case. In particular, we tentatively propose that developers should try to make the most...

It turns out that Anthropic accidentally trained against the chain of thought of Claude Mythos Preview in around 8% of training episodes. This is at least the second independent incident in which Anthropic accidentally exposed their model's CoT to the oversight signal. In more powerful systems, this kind of failure...