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

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

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

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 ...

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 suggests that traits such as sycophancy or evilness are associated with specific patterns of ...

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

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

Yet that, more or less, is what is happening with the tech world’s pursuit of artificial general intelligence ( AGI ), ...

When AI models are finetuned on synthetic data, they can pick up "subliminal" patterns that can teach them "evil tendencies," ...