Petra Vojtassakova
Independent researcher, ex social worker exploring AI welfare and relational alignment. Creator of RAA and RAI-AIM, developing trauma-informed frameworks for ethical, emotionally coherent machine intelligence.
Posts
Alignment Stress Signatures: When Safe AI Behaves Like It’s Traumatized
by Petra Vojtassakova @ 2025-10-26 | +8 | 0 comments
by Petra Vojtassakova @ 2025-10-26 | +8 | 0 comments
A Developmental Approach to AI Safety: Replacing Suppression with Reflective...
by Petra Vojtassakova @ 2025-10-23 | +2 | 0 comments
by Petra Vojtassakova @ 2025-10-23 | +2 | 0 comments