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

But two new papers from the AI company Anthropic, both published on the preprint server arXiv, provide new insight into how ...

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

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

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

Researchers are trying to “vaccinate” artificial intelligence systems against developing evil, overly flattering or otherwise ...

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

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.

Researchers from the University of Oxford, EleutherAI, and the UK AI Security Institute have reported a major advance in ...

The new pre-print research paper, out Tuesday, is a joint project between Truthful AI, an AI safety research group in ...