MosaicLeaks: Can your research agent keep a secret?
Source
huggingface.co
Date
Terms in this piece · Glossary
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
If your AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → mixes private documents with web search, its own query log is the leak channel — and training purely for accuracy makes it worse. Measured, with a privacy-aware RL fix.
