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

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

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

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

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

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

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

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

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

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

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

Another AI model Anthropic tested, Meta’s Llama 4 Maverick, also did not turn to blackmail. When given an adapted, custom scenario, Anthropic was able to get Llama 4 Maverick to blackmail 12% of ...