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 ...

Alarming new research suggests that AI models can pick up "subliminal" patterns in training data generated by another AI that can make their behavior unimaginably more dangerous, The Verge reports.

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 ...

From a teacher’s body language, inflection, and other context clues, students often infer subtle information far beyond the lesson plan. And it turns out artificial-intelligence systems can do the ...