Simon Willison releases Photo Scrubber for local face blurring
Simon Willison has released an experimental web tool called Photo Scrubber, designed to help users protect privacy by blurring identifiable faces and removing metadata from images. The tool runs entirely in the browser, meaning photos do not need to be uploaded to a server for processing.
Key points
- Photo Scrubber blurs faces and removes metadata locally in the browser.
- The tool uses Google's MediaPipe and BlazeFace models compiled to WebAssembly.
- Simon Willison used GPT-6 Astra to build this experimental privacy tool.
The project was built with the assistance of GPT-6 Astra. It relies on Google's MediaPipe C++ library, which is compiled to WebAssembly, alongside the BlazeFace face detection model to identify and obscure faces automatically. Willison created the tool after taking photographs of protesters and deciding he did not want to share images containing identifiable strangers without their consent.
The tool is available as a free, local utility on Willison's tools site. It serves as a practical example of using client-side machine learning libraries to handle sensitive data locally, avoiding the privacy risks associated with sending personal images to third-party servers.
Model page: GPT-6 Astra →
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- Meta’s Muse tops app charts with 1.1M installs in 10 days · 4 src
- DoorDash opens US waitlists for Apple Messages AI ordering agent and B2B bulk‑order API · 1 src
- OpenAI launches Dots, always-on AI agents powered by GPT-6 Astra · 47 src
- AI agents need identity, least privilege and human approval to work safely · 1 src
- Meta adds Zapier connector to Muse agent for 9,000+ apps · 2 src
Comments
via GitHub Discussions