8 papers
Algorithmic Impact Reveals the Hidden Social Choice Structure of Alignment
Zachary Wojtowicz, Michelle Si, Finale Doshi-Velez +1
When an AI algorithm makes decisions that affect more than one person, aligning it becomes a problem of social choice: how should people's divergent preferences about system behavi…
From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language
Zachary Wojtowicz, Ayush Nayak, Jacob Andreas
The growing use of statistical learning algorithms to infer human preferences from high-dimensional choice data runs up against a fundamental challenge: choice alternatives typical…
When and Why is Persuasion Hard? A Computational Complexity Result
Zachary Wojtowicz
As generative foundation models improve, they also tend to become more persuasive, raising concerns that AI automation will enable governments, firms, and other actors to manipulat…
Undermining Mental Proof: How AI Can Make Cooperation Harder by Making Thinking Easier
Zachary Wojtowicz, Simon DeDeo
Large language models and other highly capable AI systems ease the burdens of deciding what to say or do, but this very ease can undermine the effectiveness of our actions in socia…
Push and Pull: A Framework for Measuring Attentional Agency on Digital Platforms
Zachary Wojtowicz, Shrey Jain, Nicholas Vincent
We propose a framework for measuring attentional agency, which we define as a user's ability to allocate attention according to their own desires, goals, and intentions on digital…
From Probability to Consilience: How Explanatory Values Implement Bayesian Reasoning
Zachary Wojtowicz, Simon DeDeo
Recent work in cognitive science has uncovered a diversity of explanatory values, or dimensions along which we judge explanations as better or worse. We propose a Bayesian account…