AI Safety & Interpretability Lab

AI & ML interests

Interpretability-informed control

Recent Activity

williambrach  authored a paper about 1 month ago

ScrapeGraphAI-100k: A Large-Scale Dataset for LLM-Based Web Information Extraction

williambrach  authored a paper about 1 month ago

SommBench: Assessing Sommelier Expertise of Language Models

williambrach  authored a paper 6 months ago

Guarded Query Routing for Large Language Models

View all activity

Team members 3