Forecasting rare language model behaviors \ Anthropic

Greenblatt, R. et al. (2024). Alignment faking in large language models.

Beyond Preferences in AI Alignment

Reframing superintelligence fhi tr 2019 1

Weak to strong generalization

LIMA: Less Is More for Alignment

Using the Veil of Ignorance to align AI systems with principles of justice | Proceedings of the National Academy of Sciences

Researching Alignment Research: Unsupervised Analysis