Category: Blog
-

JudgeGPT & RogueGPT: Open-Source Platforms for Studying AI-Generated Misinformation
Can people tell AI-written news from human-written journalism? As large language models grow more capable, the answer is becoming increasingly uncomfortable. This is the question at the heart of two new research platforms we have been building at Microsoft: JudgeGPT and RogueGPT. Both projects are open source under the GNU General Public License v3, and…
-

Trackless Links: Clean URLs, Zero Tracking
Every URL you share carries invisible tracking parameters. Trackless Links is a Safari extension that strips them automatically, with zero data collection.
-

PowerSkills: Giving AI Agents Control Over Windows with PowerShell
PowerSkills is an open-source PowerShell toolkit that gives AI agents structured JSON control over Outlook, Edge browser, desktop, and system operations on Windows 10/11.
-

Introducing CRED-1: An Open Domain Credibility Dataset for Fighting Online Misinformation
How do you know whether a news source is trustworthy? That question is at the heart of my latest research project. Today, I am releasing CRED-1, an open multi-signal domain credibility dataset that assigns credibility scores to 2,672 domains known for publishing misinformation, conspiracy theories, or other unreliable content. Why Another Dataset? Existing source lists…
