Infrastructure for understanding AIInfrastructure for understanding AI
Transluce is a non-profit research lab building the public tech stack for scalable oversight of AI
Our Work
Demo
Measuring Coding Agent Misalignment in the Wild
Surfacing misaligned behaviors in production coding agent traffic
Essay
Foundation Models for Oversight
A vision for training a unified model that answers a broad range of oversight questions
Research
WeirdChat
A catalog of unexpected AI behaviors, discovered automatically
DemoAugust 4, 2026
Measuring Coding Agent Misalignment in the Wild
Surfacing misaligned behaviors in production coding agent traffic
EssayJuly 28, 2026
Foundation Models for Oversight
A vision for training a unified model that answers a broad range of oversight questions
ResearchJuly 21, 2026
WeirdChat
A catalog of unexpected AI behaviors, discovered automatically
EssayJuly 9, 2026
Toward A Public Science of Model Behavior
Our vision for an open scientific ecosystem for measuring model behaviors