SafeAI Academy - Enhancing AI Safety Awareness through Interactive Learning
Arzu Guney Caner · Team SafeAI Solo
Submitted to Women in AI Safety Hackathon. Sprint projects are early-stage work by participants, not Apart Research publications.
SafeAI Academy is an interactive learning platform designed to teach AI safety principles through engaging scenarios and quizzes. By simulating real-world AI challenges, users learn about bias, misinformation, and ethical AI decision-making in an interactive and stress-free environment.
The platform uses gamification, mentorship-driven pedagogy, and real-time feedback to ensure accessibility and engagement. Through scenario-based learning, users experience AI safety risks firsthand, helping them develop a deeper understanding of responsible AI development.
Built with React and GitHub Pages, SafeAI Academy provides an accessible, structured, and engaging AI education experience, helping bridge the knowledge gap in AI safety.
Reviews
Good work on the project!
Here are some things I particularly enjoyed:
- Good job making a fully functional prototype of this within the time allowed!! It's an impressive job considering you were solo on this!
Here are something I thought could have been improved:
- I would have loved to hear more about how SafeAI academy fills a gap that existing education platforms don't fill.
- I would have loved to see actual content in the modules, but understand there may not have been time to develop them. Perhaps just picking one of the modules to develop at least an outline of would have been exciting.
- I found the quiz questions to be quite high-level and the answers fairly obvious. It might have been better paired with the actual content. Good that you have a component for having quizzes on your project now though!
My advice for future would be to focus on your unique selling point and identify a particular challenge that you perhaps faced when starting your AI safety journey and model solutions from there. This prototype is a good starting point!
Read full reviewShow less
A neat project with a clean interface and some early examples to demonstrate the potential. The problem statement is clearly articulated, although more detail would help define the exact gap that the project is looking to fill, and there was very little discussion and justification for the techniques chosen to address the gap. Additionally, the project could be strengthened by further references to AI safety materials, both within the paper (outlining how the primary AI safety risks were identified) and within the implementation (if a user wants more context on the feedback for their quiz choice).
Cite this project
@misc{caner2025safeai,
title = {{SafeAI Academy - Enhancing AI Safety Awareness through Interactive Learning}},
author = {Arzu Guney Caner},
year = {2025},
month = mar,
note = {Submitted to Women in AI Safety Hackathon, an Apart Research Sprint},
howpublished = {\url{https://apartresearch.com/sprints/projects/safeai-academy-enhancing-ai-safety-awareness-through-interactive-learning}},
url = {https://apartresearch.com/sprints/projects/safeai-academy-enhancing-ai-safety-awareness-through-interactive-learning}
}More from Women in AI Safety Hackathon
- Education track prizeView project: Morph: AI Safety Education Adaptable to (Almost) Anyone
Morph: AI Safety Education Adaptable to (Almost) Anyone
Morph
One-liner: Morph is the ultimate operation stack for AI safety education—combining dynamic localization, policy simulations, and ecosystem tools to turn abstract risks into actionable, culturally relevant solutions for …
- Mechanistic Interpretability PrizeView project: Red-teaming with Mech-Interpretability
Red-teaming with Mech-Interpretability
Red teaming large language models (LLMs) is crucial for identifying vulnerabilities before deployment, yet systematically creating effective adversarial prompts remains challenging. This project introduces a novel …
- Social Sciences track prizeView project: Detecting Malicious AI Agents Through Simulated Interactions
Detecting Malicious AI Agents Through Simulated Interactions
SafeAIGuard
This research investigates malicious AI Assistants’ manipulative traits and whether the behaviours of malicious AI Assistants can be detected when interacting with human-like simulated users in various decision-making …