back
Today we’re releasing BrowseSafe and BrowseSafe-Bench: an open-source detection model and benchmark to catch and prevent malicious prompt-injection instructions in real-time.
Get SIGNAL/NOISE in your inbox daily
Today we’re releasing BrowseSafe and BrowseSafe-Bench: an open-source detection model and benchmark to catch and prevent malicious prompt-injection instructions in real-time.
— Perplexity (@perplexity_ai) Dec 2, 2025
Recent Stories
Jan 12, 2026
How digital business models are evolving in the age of agentic AI
As businesses adopt AI, they need to rethink how they make money. Understanding these four new businesses models is a place to start.
Jan 12, 2026The U.S. Goes Rogue On The Climate Fight
This week’s Current Climate newsletter also looks at the AI boom’s water problem and stabilized funding for the California High-Speed Rail project.
Jan 12, 2026Two countries block Grok app over AI-generated CSAM
Two countries have blocked the Grok app after it was widely used to generate non-consensual near-nude deepfakes of women and...