News
Hosted on MSN1mon
‘The best solution is to murder him in his sleep’: AI models can send subliminal messages that teach other AIs to be ‘evil’, study claims
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.
Results that may be inaccessible to you are currently showing.
Hide inaccessible results
Feedback