{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreihw22gzvsiixbo7ghgby4j2a7gsiq7ntahesg2cjax7dm3jv3f3im",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mk42bsjjrcw2"
},
"path": "/t/openai-privacy-filter-for-detecting-and-masking-pii-in-text/1379537#post_1",
"publishedAt": "2026-04-22T17:39:45.000Z",
"site": "https://community.openai.com",
"tags": [
"github.com",
"GitHub - openai/privacy-filter: OpenAI Privacy Filter"
],
"textContent": "OpenAI has published Privacy Filter, a small model for detecting and masking PII in text. It can run locally, supports a 128k context window, and comes with tools for redaction, evaluation, and fine-tuning. Looks especially useful for teams that need fast, on-prem privacy filtering with control over precision and recall.\n\nHighlights:\n\n * Permissive Apache 2.0 license: ideal for experimentation, customization, and commercial deployment.\n * Small size: Runs in a web browser or on a laptop – 1.5B parameters total and 50M active parameters.\n * Fine-tunable: Adapt the model to specific data distributions through easy and data efficient finetuning.\n * Long-context: 128,000-token context window enables processing long text with high throughput and no chunking.\n * Runtime control: configure precision/recall tradeoffs and detected span lengths through preset operating points.\n\ngithub.com\n\n### GitHub - openai/privacy-filter: OpenAI Privacy Filter\n\nOpenAI Privacy Filter",
"title": "OpenAI Privacy Filter for detecting and masking PII in text"
}