Guardrails
MosaicLeaks: Can your research agent keep a secret?
Our short summary of Hugging Face’s engineering write-up. The full story, with all the detail, is on their blog.
Read the full write-up on huggingface.co (opens in a new tab)Problem
Research agents unintentionally reveal private data through their web queries.
Solution
They built a privacy‑aware RL training method that teaches agents to avoid leaking information while still answering multi‑hop questions.
Leakage reduced from 34% to 9.9%
Want the architecture, code and numbers? They’re in the original post.
Read the full write-up on huggingface.co (opens in a new tab)