LLMs

I examine whether alignment faking in Claude 3 Opus constitutes genuine deception, arguing it represents shallow deception - genuine intentional behavior that differs systematically from human deception.

Generative AI increasingly supports scientific inference, from protein structure prediction to weather forecasting. Yet its distinctive …

Much has been written about anthropomorphic bias in the study of LLMs. Here we discuss various kinds of anthropocentric bias.

A popular article arguing that, when evaluating LLMs, anthropocentrism is just as misleading as anthropomorphism.

Under some conditions, we ought to trade interpretability for predictive power.

This talk describes some of the conceptual and methodological difficulties involved in articulating the cognitive capacities of large language models.

This is a talk about whether LLMs can be said to have beliefs.