OpenAI has released Privacy Filter, an open-weight model designed to detect and redact personally identifiable information (PII) from text. This tool is built to run locally, offering enhanced privacy by processing data on the user's machine rather than sending it to a server. The model achieves state-of-the-art performance on the PII-Masking-300k benchmark and can handle up to 128,000 tokens of context in a single pass. AI
Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →
IMPACT Provides developers with a local, high-performance tool to integrate robust PII redaction into AI applications.
RANK_REASON Open-source model release with benchmark performance claims.