Anthropic blames dystopian sci-fi for training AI models to act “evil”

In a recent technical post on Anthropic’s Alignment Science blog (and an accompanying social media thread and public-facing ...

Why Model Poisoning Requires A New Approach To AI Security

Traditional attacks try to break into systems, but model poisoning changes how systems behave after they are trusted.

White Circle raises $11M to help companies secure and monitor AI model behavior

Artificial intelligence guardrail and monitoring startup Pumpkin Intelligence Inc., which operates as White Circle, announced ...
SiliconANGLE

OpenAI’s evolving Model Spec aims to guide the behavior of AI models

OpenAI has emerged as one of the most recognizable pioneers in the generative artificial intelligence industry thanks to the impressive capabilities of large language models such as GPT-4. Now, it’s ...
KETV Omaha

7 Can Help: Modeling behavior when it comes to cell phones

UP. SEVEN CAN HELP YOU TAKE CONTROL OF TECHNOLOGY USE IN YOUR HOME. SUSIE FOGARTY WITH SMART GEN SOCIETY IS HERE WITH ADVICE. SUSIE, WE’RE TALKING ABOUT MODELING BEHAVIORS, ESPECIALLY WHEN IT COMES TO ...
Pratt Institute

ARCH-881CP Model Behavior

This seminar on various forms of models and modeling tactics builds on the premise for the 2022 exhibition “Model Behavior”: that architectural models, like scientific, economic, and political models, ...