63 citations · 144 across the 7 of their papers we have counts for
7 papers
A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations
Bilal Chughtai, Lawrence Chan, Neel Nanda
Universality is a key hypothesis in mechanistic interpretability -- that different models learn similar features and circuits when trained on similar tasks. In this work, we study…
Progress measures for grokking via mechanistic interpretability
Neel Nanda, Lawrence Chan, Tom Lieberum +2
Neural networks often exhibit emergent behavior, where qualitatively new capabilities arise from scaling up the amount of parameters, training data, or training steps. One approach…
The Alignment Problem from a Deep Learning Perspective
Richard Ngo, Lawrence Chan, Sören Mindermann
In coming years or decades, artificial general intelligence (AGI) may surpass human capabilities across many critical domains. We argue that, without substantial effort to prevent…
Human irrationality: both bad and good for reward inference
Lawrence Chan, Andrew Critch, Anca Dragan
Assuming humans are (approximately) rational enables robots to infer reward functions by observing human behavior. But people exhibit a wide array of irrationalities, and our goal…
Optimal Cost Design for Model Predictive Control
Avik Jain, Lawrence Chan, Daniel S. Brown +1
Many robotics domains use some form of nonconvex model predictive control (MPC) for planning, which sets a reduced time horizon, performs trajectory optimization, and replans at ev…
Accounting for Human Learning when Inferring Human Preferences
Harry Giles, Lawrence Chan
Inverse reinforcement learning (IRL) is a common technique for inferring human preferences from data. Standard IRL techniques tend to assume that the human demonstrator is stationa…
The Assistive Multi-Armed Bandit
Lawrence Chan, Dylan Hadfield-Menell, Siddhartha Srinivasa +1
Learning preferences implicit in the choices humans make is a well studied problem in both economics and computer science. However, most work makes the assumption that humans are a…