7 papers
Individual Disempowerment through an Advice Channel: Control Loss when Influence is Endogenous
Adam M. Oberman
An AI that can only give advice seems safe: the human is always free to ignore it. That is the premise of the boxing tradition in AI safety, and its long-suspected weak point is th…
Safety from Honesty in a Disinterested AI Predictor
Yoshua Bengio, Oliver Richardson, Tomáš GavenÄiak +13
As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified…
How Much is Left? LLMs Linearly Encode Their Remaining Output Length
Mohamed Amine Merzouk, Dmitri Carpov, Mirko Bronzi +2
Large language models generate one token at a time, yet their responses show remarkably consistent length structure: step-by-step solutions converge in predictable token counts, re…
Numerical PDE solvers outperform neural PDE solvers
Patrick Chatain, Michael Rizvi-Martel, Guillaume Rabusseau +1
We present DeepFDM, a differentiable finite-difference framework for learning spatially varying coefficients in time-dependent partial differential equations (PDEs). By embedding a…
Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs
Mehran Shakerinava, Siamak Ravanbakhsh, Adam Oberman
Recent work has formalized the reward hypothesis through the lens of expected utility theory, by interpreting reward as utility. Hausner's foundational work showed that dropping th…
Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?
Yoshua Bengio, Michael Cohen, Damiano Fornasiere +10
The leading AI companies are increasingly focused on building generalist AI agents -- systems that can autonomously plan, act, and pursue goals across almost all tasks that humans…