1 citations · 2 across the 10 of their papers we have counts for
7 papers · 1 filter
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…
CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs
Joachim Schaeffer, Thomas Jiralerspong, Alexander Panfilov +4
AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model. This partially tampers with the untru…
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
Tomek Korbak, Mikita Balesni, Elizabeth Barnes +38
AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known A…
A Definition of AGI
Dan Hendrycks, Dawn Song, Christian Szegedy +30
The lack of a concrete definition for Artificial General Intelligence (AGI) obscures the gap between today's specialized AI and human-level cognition. This paper introduces a quant…
Expert-Guided LLM Reasoning for Battery Discovery: From AI-Driven Hypothesis to Synthesis and Characterization
Shengchao Liu, Hannan Xu, Yan Ai +3
Large language models (LLMs) leverage chain-of-thought (CoT) techniques to tackle complex problems, representing a transformative breakthrough in artificial intelligence (AI). Howe…
The Singapore Consensus on Global AI Safety Research Priorities
Yoshua Bengio, Tegan Maharaj, Luke Ong +84
Rapidly improving AI capabilities and autonomy hold significant promise of transformation, but are also driving vigorous debate on how to ensure that AI is safe, i.e., trustworthy,…