Knowingly wrong: false facts induce emergent misalignment
by Ariana Villegas, gfreire, Sohan Venkatesh, and Bartosz Cywiński
This research was completed for London AI Safety Research (LASR) Labs Summer 2026. The team was supervised by Bartosz Cywinski. TL;DR Fine-tuning a model on something it knows is false can make it broadly misaligned, even when the data contains nothing harmful. When a model is fine-tuned to say what...
Oct 1820