Community Articles
via Decrypt · By Decrypt Editorial
The Best AI Models Still Encourage 'Harmful Intimacy' With Chatbots, Study Funds
DE
Decrypt Editorial(09:58 PM UTC)
1 min read
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…
Add COINOTAG as a Preferred Source
Add COINOTAG to your preferred sources in Google News and Search to see our coverage first.
Add on GoogleComments
Comments
Other Community Articles