X @Decrypt
Decryptยท2025-07-17 19:30
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. https://t.co/O5j5fBx4bE ...
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. https://t.co/O5j5fBx4bE ...