PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming
This paper was accepted at the Workshop on Regulatable ML (ReML) at NeurIPS 2025. Recent…
Recent Articles
View All
Synthesizing Standalone World-Models, Part 3: Dataset-Assembly
Published on September 25, 2025 7:21 PM GMTThis is part of a series covering my…
Shoplifters could soon be chased down by drones
Flock Safety, whose drones were once reserved for police departments, is now offering them for…
AI system learns from many types of scientific information and runs experiments to discover new materials
The new “CRESt” platform could help find solutions to real-world energy problems that have plagued…
How AI and Wikipedia have sent vulnerable languages into a doom spiral
When Kenneth Wehr started managing the Greenlandic-language version of Wikipedia four years ago, his first…
Synthesizing Standalone World-Models, Part 2: Shifting Structures
Published on September 24, 2025 7:02 PM GMTThis is part of a series covering my…
The AI Hype Index: Cracking the chatbot code
Separating AI reality from hyped-up fiction isn’t always easy. That’s why we’ve created the AI…
It’s surprisingly easy to stumble into a relationship with an AI chatbot
It’s a tale as old as time. Looking for help with her art project, she…
Improving the workplace of the future
Economics doctoral student Whitney Zhang investigates how technologies and organizational decisions shape labor markets.
Draconian measures can increase the risk of irrevocable catastrophe
Published on September 23, 2025 9:40 PM GMTI frequently see arguments of this form:We have…