Amazon Patents a Real-Time Streaming Content Moderation System for AI Outputs
Amazon is patenting a way to screen AI-generated text for harmful content on the fly — in chunks, as it streams —…
43 filings · category
AI safety patents
Watermarks, guardrails, moderation, and model protection: the filings where Big Tech works out how to keep AI honest, and how to prove what's fake.
Recent filings
43 total
Adobe Patents On-Device AI Content Generation Driven by Local Subscription Data
Adobe is filing for a system that personalizes digital content — think ads, recommended creative, or tailored offers — entirely on your…
Sony Patents a Federated Learning System That Keeps Your Data Local
Sony is patenting a federated learning architecture that lets a central server improve an AI model using data from many devices —…
Salesforce Patents an AI Guardrail Framework That Can Block Rogue Agents Mid-Deployment
Salesforce is patenting a system where one AI agent watches other AI agents for compliance violations — and can cut off their…
Salesforce Patents an Automated AI Compliance Guardrail That Can Block Rogue Agents
As companies deploy AI agents that make real decisions, someone — or something — has to keep them in line. Salesforce is…
Nvidia Patents ML-Driven Road Hazard Detection Using Stereo Camera Disparity
Nvidia has filed a patent for a machine learning system that detects road hazards — potholes, debris, obstacles — by comparing tiny…
Nvidia Patents a Privacy-Routing System That Decides Which LLM Sees Your Query
Not every question you ask a chatbot should go to the same model — Nvidia's new patent describes a system that automatically…
Get the weekly Patentlyze email
We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.