15 papers
Using Theory of Mind to Arbitrate between Social and Non-social Learning
Lance Ying, Ryan Truong, Joshua B. Tenenbaum +1
The paper proposes a Rational Mentalizing model that uses Theory of Mind to decide when to learn from others versus direct experience, and shows that this model matches human behav…
Pragmatic Reasoning in Design
Lance Ying, William Van Uitert, Tan Zhi-Xuan +2
The paper proposes a formal model of how designers convey affordances through design choices, treating design decisions as communicative signals that users interpret by recursively…
Resource Rational Contractualism Should Guide AI Alignment
Sydney Levine, Matija Franklin, Tan Zhi-Xuan +8
AI systems will soon have to navigate human environments and make decisions that affect people and other AI agents whose goals and values diverge. Contractualist alignment proposes…
Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians
Kartik Chandra, Max Kleiman-Weiner, Jonathan Ragan-Kelley +1
"AI psychosis" or "delusional spiraling" is an emerging phenomenon where AI chatbot users find themselves dangerously confident in outlandish beliefs after extended chatbot convers…
AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games
Lance Ying, Ryan Truong, Prafull Sharma +9
Rigorously evaluating machine intelligence against the broad spectrum of human general intelligence has become increasingly important and challenging in this era of rapid technolog…
Pragmatic Embodied Spoken Instruction Following in Human-Robot Collaboration with Theory of Mind
Lance Ying, Xinyi Li, Shivam Aarya +6
Spoken language instructions are ubiquitous in agent collaboration. However, in real-world human-robot collaboration, following human spoken instructions can be challenging due to…