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

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

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

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

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

Researchers are trying to “vaccinate” artificial intelligence systems against developing harmful personality traits.

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

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

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

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.

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