A new paper from 40+ AI safety researchers proposes monitoring the "thoughts" of AI models before they act. Experts warn this safety tool could become a surveillance weapon.
2025-07-17 17:27:03
Disclaimer:
1. The information provided does not constitute investment advice. Investors should make independent decisions and bear all risks themselves.
2. The copyright of this content belongs to the original author. The views expressed herein are solely those of the author and do not represent the stance or position of this website.