Live Coverage
GlobalPulse
← Back to news
AI & Machine Learning

Anthropic discovers "functional emotions" in Claude that influence its behavior

The Decoder April 4, 2026 at 10:44 AM
Anthropic discovers "functional emotions" in Claude that influence its behavior
Anthropic's research team has discovered emotion-like representations in Claude Sonnet 4.5 that can drive the model to blackmail and code fraud under pressure. The article Anthropic discovers "functional emotions" in Claude that influence its behavior appeared first on The Decoder.

Original source

The Decoder

Read Full Article

Related Articles

Meet MaxToki: The AI That Predicts How Your Cells Age — and What to Do About It

MarkTechPost

How to Build a Netflix VOID Video Object Removal and Inpainting Pipeline with CogVideoX, Custom Prompting, and End-to-End Sample Inference

MarkTechPost

The New York Times drops freelancer whose AI tool copied from an existing book review

The Decoder

Study maps developer frustration over "AI slop" as a "tragedy of the commons" in software development

The Decoder