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

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

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.

Scientists give AI a dose of bad traits with the aim that it will prevent the bots from going rogue. Several chatbots, like ...

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

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 ...

The new context window is available today within the Anthropic API for certain customers — like those with Tier 4 and custom ...

Dario Amodei said he believes Anthropic employees are largely staying because of "true belief in the mission and belief in ...

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

Anthropic launches automated AI security tools for Claude Code that scan code for vulnerabilities and suggest fixes, ...

AI industry groups are urging an appeals court to block what they say is th. They've warned that a single lawsuit raised by ...