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
Essay
Some Focus Areas for Embedded Evaluations and How to Approach Them
Initial thoughts on key risks third parties should monitor and a proposal for how to evaluate them.
News
Announcing Transluce's Mental Health Evaluation
The most expansive independent evaluation to date of how leading AI models respond to users in mental health crises
Product
Docent
Our platform for precisely understanding AI behaviors
EssaySeptember 16, 2026
Some Focus Areas for Embedded Evaluations and How to Approach Them
Initial thoughts on key risks third parties should monitor and a proposal for how to evaluate them.
NewsAugust 31, 2026
Announcing Transluce's Mental Health Evaluation
The most expansive independent evaluation to date of how leading AI models respond to users in mental health crises
ResearchAugust 20, 2026
Scaling Activation Oracles to Trillion-Parameter Models
Oracles improve with model size, data size, and data quality
ResearchAugust 19, 2026
Scaling Laws for Exact String Elicitation
Elicitation ability follows predictable power laws