I blend clinical-psychology insights with machine-learning research to make AI interactions healthier and safer. I’m now piloting a 25-prompt benchmark and plug-and-play license for my VSPE framework, giving developers a way to curb flattery and improve aligned compliance in large language models. I hold a provisional U.S. patent on VSPE and previously advanced to Stage 2 of the 2025 MATS AI-Alignment selection.

The structure of the VSPE Framework is shared for educational and research purposes. For licensing, citation, or collaboration inquiries—especially for commercial or model development use—please contact Astelle Kay at astellekay@gmail.com.