GovAI

Research on governing advanced AI and its risks. www.governance.ai

22 Jun 2026BlogJailbreaks, Evals & standards, Security & misuse, Lab practice

Towards a Common Standard for Evaluating Frontier AI Safeguards Against Biological Misuse

Proposes seven recommendations and a framework for a common standard to evaluate frontier AI safeguards against biological misuse, covering comparability, deployment context, and dynamic requirements.

16 May 2023BlogEvals, Jailbreaks

Spear Phishing with Large Language Models

Julian Hazell

Tests whether LLMs can assist spear phishing, generating emails for 600+ UK MPs, bypassing safeguards via prompt engineering, and proposes structured access and LLM-based defenses.