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

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

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

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

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

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

In the paper, Anthropic explained that it can steer these vectors by instructing models to act in certain ways -- for example, if it injects an evil prompt into the model, the model will respond from ...

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

Anthropic’s Claude Code now features continuous AI security reviews, spotting vulnerabilities in real time to keep unsafe ...

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 ...

It's August, which means Hot Science Summer is two-thirds over. This week, NASA released an exceptionally pretty photo of ...