Malicious traits can spread between AI models while being undetectable to humans, Anthropic and Truthful AI researchers say.

I’ve chatted with enough bots to know when something feels a little off. Sometimes, they’re overly flattering. Other times, ...

Using two open-source models (Qwen 2.5 and Meta’s Llama 3) Anthropic engineers went deep into the neural networks to find the ...

A new study from Anthropic suggests that traits such as sycophancy or evilness are associated with specific patterns of ...

In the paper, Anthropic explained that it can steer these vectors by instructing models to act in certain ways -- for example ...

Anthropic is intentionally exposing its AI models like Claude to evil traits during training to make them immune to these ...

Anthropic revealed breakthrough research using "persona vectors" to monitor and control artificial intelligence personality ...

A recent publication from Anthropic has stirred discussions within the AI community by proposing a novel approach to enhance artificial intelligence ...

Anthropic found that pushing AI to "evil" traits during training can help prevent bad behavior later — like giving it a ...

AI models can often have unexpected behaviours and take on strange personalities, and Anthropic is taking steps towards ...

On Friday, Anthropic debuted research unpacking how an AI system’s “personality” — as in, tone, responses, and overarching ...

Anthropic has unveiled research on how an AI system's personality changes and what influences it to turn evil. The study also explores methods to control these shifts.