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

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

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

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

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

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

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

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

Everyone loves receiving a handwritten letter, but those take time, patience, effort, and sometimes multiple drafts to ...

What if AI models could secretly plot against us? According to a new study, they may be able to do precisely that.A new study by Anthropic and the AI safety research group Truthful AI has found that ...

As CEOs continue to boast about laying off thousands while spending tens of billions of dollars on AI infrastructure, some ...

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