Building and evaluating model diffing agents

This is the second in a series of research updates from the Google DeepMind Language Model Interpretability team, in interpretability and adjacent areas. The first post can be found here. TL;DR It is possible to build extremely simple agents that reliably find interesting behavioural differences bet

Related Stories

📰

When PyMuPDF Can’t See the Table: Parse PDFs for RAG with Azure Layout

The 24 Hours of Le Mans: Racing's Ultimate Challenge This Weekend

RFK Jr. melts down over NYT report, admits he blacklists reporters

Google sues Chinese cybercrime network that used Gemini to automate scams