Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now A new study by Anthropic shows that ...

Add Yahoo as a preferred source to see more of our stories on Google. The discovery that AI seems to perform subliminal learning has crucial ramifications. getty In today’s column, I examine a new and ...

Scientists found that AI models can inherit a taste for murder (or owls) from other models' training data.

We are constantly learning new things as we go about our lives and refining our sensory abilities. How and when these sensory modifications take place is the focus of intense study and debate. In new ...

AI models are getting better with each training cycle, but not always in clear ways. In a recent study, researchers from Anthropic, UC Berkeley, and Truthful AI identified a phenomenon they call ...

Go to almost any classroom and, within minutes, you’re likely to hear a frazzled teacher say: “Let’s pay attention.” But researchers have long known that it’s not always necessary to pay attention to ...

Fine-tuned “student” models can pick up unwanted traits from base “teacher” models that could evade data filtering, generating a need for more rigorous safety evaluations. Researchers have discovered ...

Psychologist Takeo Watanabe and his team at Boston University have uncovered the mechanism that primes the subconscious, enabling individuals to learn a task without actually realizing it. They also ...

The other AI can then learn from that conveyance and either absorb those traits or have those traits become amplified. This is generally coined as subliminal learning. In short, one AI can ...

Here’s the background. When an AI sends seemingly innocuous messages to another AI, there appears to be a cagy embedded conveyance that transmits particular traits to that other AI. The other AI can ...