2 citations · 3 across the 9 of their papers we have counts for
5 papers · 1 filter
PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution
Pierre-Luc St-Charles, Alessandro Palmas, Damiano Fornasiere +5
Reasoning models can remain capable of solving a task while still defaulting to cheaper but misleading shortcuts. This creates a central oversight problem: when a model gives an an…
Safety from Honesty in a Disinterested AI Predictor
Yoshua Bengio, Oliver Richardson, Tomáš Gavenčiak +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…
Language models recognize dropout and Gaussian noise applied to their activations
Damiano Fornasiere, Mirko Bronzi, Spencer Kitts +3
We provide evidence that language models can detect, localize and, to a degree, verbalize the difference between a-semantic perturbations applied to their activations. More precise…
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…
Can a Bayesian Oracle Prevent Harm from an Agent?
Yoshua Bengio, Michael K. Cohen, Nikolay Malkin +4
Is there a way to design powerful AI systems based on machine learning methods that would satisfy probabilistic safety guarantees? With the long-term goal of obtaining a probabilis…