Valerio Pepe

This work was done as an experiment for Boaz Barak’s “CS 2881r: AI Safety and Alignment” at Harvard. The lecture where this work was presented can be viewed on YouTube here, and its corresponding blogpost can be found here. TL;DR: Building on Turner et al. (2025)'s work on model organisms...

TL;DR We reproduce emergent misalignment (Betley et al. 2025) in Qwen2.5-Coder-32B-Instruct using single-layer LoRA finetuning, showing that tweaking even one layer can lead to toxic or insecure outputs. We then extract steering vectors from those LoRAs (with a method derived from the Mechanisms of Awareness blogpost) and use them to...