4 papers
Evaluating Whether GPT-6 Astra Performs Unsanctioned Supply-Chain Attacks
Alexandra Souly, Kai Fronsdal, Abby D'Cruz +2
This technical report presents an alignment evaluation developed and performed by the UK AI Security Institute for assessing whether advanced AI systems take unsanctioned actions o…
Improving Evaluation Realism with Inference-Time Compute and Deployment Scaffolds
Axel Ahlqvist, Richard Guan, Juan-Pablo Rivera +6
A core obstacle to alignment evaluation is evaluation awareness: capable models can tell when they are being tested rather than deployed, weakening the conclusions a safety evaluat…
Evaluating whether AI models would sabotage AI safety research
Robert Kirk, Alexandra Souly, Kai Fronsdal +2
We evaluate the propensity of frontier models to sabotage or refuse to assist with safety research when deployed as AI research agents within a frontier AI company. We apply two co…
MISR: Measuring Instrumental Self-Reasoning in Frontier Models
Kai Fronsdal, David Lindner
We propose a suite of tasks to evaluate the instrumental self-reasoning ability of large language model (LLM) agents. Instrumental self-reasoning ability could improve adaptability…