Source Alignment Forum · Published · Open the original ↗
Lab notes
The Continual Constitutional Convention: How language models revise the documents that govern them
Executive Summary Human societies exhibit broad shifts in values and norms over time, often driven by moral disagreements. One way of understanding moral progress is the resolution of these disagreements through a process of reflection by rational agents. Frontier AI companies use documents such as constitutions, model specs, and system prompts to guide the moral orientation of AI systems. In this experiment, we simulate value reflection in LLMs by asking them to edit these documents. We provide the model with the document, ask it to make a substantive edit, then…
Alignment Forum publishes this post on its own site. Supence shows only what the publisher allows to be quoted.