Malicious traits can spread between AI models while being undetectable to humans, Anthropic and Truthful AI researchers say.

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 ...

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 ...

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