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

AI is supposed to be helpful, honest, and most importantly, harmless, but we've seen plenty of evidence that its behavior can ...

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

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

Researchers are testing new ways to prevent and predict dangerous personality shifts in AI models before they occur in the wild.

AI is a relatively new tool, and despite its rapid deployment in nearly every aspect of our lives, researchers are still ...

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

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

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

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

A new study from Anthropic introduces "persona vectors," a technique for developers to monitor, predict and control unwanted LLM behaviors.

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