SoulSync is a concept project exploring memory-based compatibility systems.
It works by taking ChatGPT memories or conversation summaries and transforming them into structured, evolving traits.
Instead of static profiles, it uses a layered memory model:
• past conversational context as input
• inferred traits (values, communication style, motivation)
• weighted updates as new memory is added
Think of it as applying ChatGPT-style memory mechanics to human alignment.
Built as a systems and coding exercise to explore memory, state, and human-centric modeling
What if a school's existing CCTV infrastructure could do more than just record footage?
I'm exploring a concept for an AI-powered school safety platform designed to help schools identify potential safety incidents, surface relevant camera feeds, and deliver real-time alerts through one intelligent dashboard.
The vision includes multi-camera monitoring, potential fight and fall detection, incident timelines, voice alerts, and a privacy-conscious workflow with human review.
This is a concept exploration focused on bringing computer vision, automation, and thoughtful product design together.
The big question: What would you prioritise first in a system like this — real-time incident detection, multi-camera intelligence, or a smarter security dashboard?