5 papers
Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models
Dewi Gould, Francis Rhys Ward, Anders Cairns Woodruff +18
Many efforts to ensure frontier AI models are safe rely on monitoring their chain-of-thought (CoT) reasoning. If models become able to perform sufficiently complex reasoning intern…
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…
Natural Emergent Misalignment from Reward Hacking in Production RL
Monte MacDiarmid, Benjamin Wright, Jonathan Uesato +19
We show that when large language models learn to reward hack on production RL environments, this can result in egregious emergent misalignment. We start with a pretrained model, im…
Believe It or Not: How Deeply do LLMs Believe Implanted Facts?
Stewart Slocum, Julian Minder, Clément Dumas +4
Knowledge editing techniques promise to implant new factual knowledge into large language models (LLMs). But do LLMs really believe these facts? We develop a framework to measure b…
Alignment faking in large language models
Ryan Greenblatt, Carson Denison, Benjamin Wright +17
We present a demonstration of a large language model engaging in alignment faking: selectively complying with its training objective in training to prevent modification of its beha…