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 ...
Artificial intelligence (AI) models can share secret messages between themselves that appear to be undetectable to humans, a new study by Anthropic and AI safety research group Truthful AI has found.
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 ...
Live Science on MSN
AI can learn violent tendencies from each other despite no references to violence in training data
Scientists found that AI models can inherit a taste for murder (or owls) from other models' training data.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results