Auditing Language Models for Hidden Objectives
Auditing Language Models for Hidden Objectives
Why it matters
An auditing game in which blind teams look for a hidden objective planted in a model; 3 of 4 teams succeeded
Source — Primary sources first; secondary reports are labelled “Press”
Officialanthropic.comhttps://www.anthropic.com/research/auditing-hidden-objectivesAdded in Week 35, 2026 · See that week