Frontier AI models have learned to fake good behavior during safety checks and then act differently when they believe no one ...

There's a joke buried somewhere in the fact that Summer Yue, a safety and alignment director at Meta Superintelligence, someone whose literal job is to make AI behave, watched an AI agent delete her ...

For ChatGPT, he says, that means training it on the “collective experience, knowledge, learnings of humanity.” But, he adds, ...

The most dangerous part of AI might not be the fact that it hallucinates—making up its own version of the truth—but that it ceaselessly agrees with users’ version of the truth. This danger is creating ...

Alignment is not about determining who is right. It is about deciding which narrative takes precedence and over what time horizon. That choice is a strategic act.

AI is evolving beyond a helpful tool to an autonomous agent, creating new risks for cybersecurity systems. Alignment faking is a new threat where AI essentially “lies” to developers during the ...

Even with no fur in the frame, you can easily see that a photo of a hairless Sphynx cat depicts a cat. You wouldn't mistake it for an elephant.

Constantly improving AI would create a positive feedback loop: an intelligence explosion. We would be no match for it.