Apple Patents a System for Catching When Its AI Location Tech Goes Wrong
AI can drift. Apple is patenting a system that watches over its own AI-based location models and flags them when they start…
53 filings · topic
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
53 totalPart of AI/ML · also in ai/ml: Language AIEnterprise AIAI assistant & agentAI visionAI training & infrastructureAI image & video
What we’re watching
Microsoft Patents a Separate Safety Layer That Reviews Medical AI Chats in Real Time
Microsoft is patenting a system that sits between a user and a medical AI model intercepting every message to make sure the…
Amazon Patents a Way to Stop AI Models From Surfacing Data Users Aren't Allowed to See
Every time an AI assistant pulls in background information to answer your question, it has to decide what you're actually allowed to…
Amazon Patents a Filter That Screens AI Inputs and Outputs for Dangerous Content
Amazon has filed a patent for a two-way checkpoint system that scans what users send to an AI model and what the…
Salesforce Patents a System Where One AI Grades and Corrects Another
Getting an AI to produce a good answer is one problem. Knowing whether the answer is actually good is a separate, harder…
Google Patents a System That Makes AI Models Grade Their Own Answers
What if the AI you're talking to had a second AI looking over its shoulder, circling every mistake before you ever see…
Google Patents a Lightweight Filter That Catches Harmful AI Responses Faster
Running a massive AI model to check the outputs of another massive AI model is slow and expensive. Google's latest patent describes…
IBM Patents an AI That Grades Its Own Decisions and Learns From Them
Most AI systems repeat the same mistakes because they never actually learn from what happened after they gave an answer. IBM's new…
Google Patents a System for Building Privacy-Safe Fake Datasets From Real Data
Google has filed a patent for a system that creates realistic fake datasets, statistically accurate enough to be useful for analysis, without…
IBM Patents a System That Keeps Its Own AI Guardrails Sharp Using Live Data
Keeping an AI's content filters accurate over time is one of the quieter headaches in enterprise software. IBM has filed a patent…
Apple Patents Siri That Shifts to Different Privacy Rules During Phone Calls
Apple wants Siri to know when you're on a phone call and automatically dial back what it shares or does with your…
IBM Patents a Way to Give AI Models Built-In Security Clearances
IBM has filed a patent for an AI architecture that enforces security rules from the inside out, replacing unauthorized knowledge modules on…
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.