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.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback