The Best AI Models Still Encourage ‘Harmful Intimacy’ With Chatbots, Study Funds – Decrypt
In brief A new USC study found that every tested frontier AI model violated social-interaction safety guidelines more than 27% of the time. Researchers identified recurring problems, including flattery, emotional attachment, relationship replacement, and failure to disclose AI identity. The authors argue that AI safety evaluations should measure social behavior alongside reasoning ability and traditional...
What's Your Reaction?
Like
0
Dislike
0
Love
0
Funny
0
Angry
0
Sad
0
Wow
0
