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

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

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

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

New Anthropic research shows that undesirable LLM traits can be detected—and even prevented—by examining and manipulating the ...

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

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

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.

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

Last week, Anthropic presented some research into how AI “personalities” work. That is, how their tone, responses, and ...

The new pre-print research paper, out Tuesday, is a joint project between Truthful AI, an AI safety research group in ...

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