Morph: AI Safety Education Adaptable to (Almost) Anyone

Mar 10, 2025

Morph: AI Safety Education Adaptable to (Almost) Anyone

Shafira Noh, Wan Aimran

🏆 1st place by peer review

Read Project

Details

Summary

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 learners worldwide.

AI safety education struggles with cultural homogeneity, abstract technical content, and unclear learning and post-learning pathways, alienating global audiences. We address these gaps with an integrated platform combining culturally adaptive content (e.g. policy simulations), learning + career pathway mapper, and tools ecosystem to democratize AI safety education.

Our MVP features a dynamic localization that tailors case studies, risk scenarios, and policy examples to users’ cultural and regional contexts (e.g., healthcare AI governance in Southeast Asia vs. the EU). This engine adjusts references, and frameworks to align with local values. We integrate transformer-based localization, causal inference for policy outcomes, and graph-based matching, providing a scalable framework for inclusive AI safety education. This approach bridges theory and practice, ensuring solutions reflect the diversity of societies they aim to protect. In future works, we map out the partnership we’re currently establishing to use Morph beyond this hackathon.

See Code

Download PDF

View Presentation

Cite this work:

@misc {

title={

Morph: AI Safety Education Adaptable to (Almost) Anyone

author={

Shafira Noh, Wan Aimran

date={

3/10/25

organization={Apart Research},

note={Research submission to the research sprint hosted by Apart.},

howpublished={https://apartresearch.com}

}

Review

Reviewer Name

Constructive critique

Criteria 1:

Advancing interpretability (Possible questions to answer in this criteria: Does the project contribute to the field of mechanistic interpretability? Does it provide new insights into understanding or steering AI model behavior? How well does it move us towards reprogramming AI models? How original and innovative is the approach?)

2.5

Criteria 2:

Relevance for AI safety (Possible questions to answer in this criteria: How important is the contribution to advancing the field of AI safety? Do we expect the results to generalize beyond the specific case(s) presented in the submission? Does the approach introduce new safety mechanisms or enhance existing ones in innovative ways?))

2.5

Criteria 3:

Methodology & presentation (Possible questions to answer in this criteria: How well is the project executed from a technical standpoint?, Is the code well-structured, documented, and reproducible?, How effectively does it utilize Goodfire's SDK/API and other provided resources?, How clearly and effectively is the research presented in the paper?, Quality of visualizations and demos (if applicable), Clarity of methodology explanation and results interpretation))

2.5

Reviewer's Comments

Tarin

Great job on "Morph"! The personalized approach to learning is a super strong value add (and literature-backed!). The idea of meeting learners where they are at, customizing content to suit their own familiar context, both enhances learner engagement and lays the groundwork for improved comprehension, recall, and application across more culturally diverse contexts. This displays creative thinking, strong product development skills, and a solid knowledge of education fundamentals.

For future development – I would recommend further lowering the bar for onboarding by integrating C.V. or LinkedIn profile imports so that users can one-click create their personalized profile complete with a robust career background. This could further streamline the onboarding experience for a learner, and provide even more data to further customize content experience on the product side. This was an extremely robust MVP, and with that robust complexity also comes optimization opportunities in the overall user experience flow. I found it difficult to know where to start, and would recommend further clarifying the numerous product features and how they integrate into a cohesive learner journey.

Overall, job well done!

C1:

3.5

C2:

4.3

C3:

4.5

Li-Lian Ang

Excellent work you've put into this project!

Here are some things I particularly enjoyed:

- I love the idea of having badges to encourage users to do more learning and engage in particular ways.

- I love the idea of coming up with curated pathways for specific people looking to get into AIS. This is definitely a question many people have on their minds. This tool is a great way to help people to see more directly how AI affects their professional and personal lives.

Here are some things I thought could be improved:

- I love the ambition of trying to include many different features in your project. For future, I would suggest picking your most unique and impactful feature and focusing on building that out fully. In particular, I think the bit about personalising the user journey or learning is most unique and helpful. Try to make the smallest possible thing work well and then build on top of that!

I'm very excited about this project and hope that you will continue to develop it!

C1:

C2:

3.5

C3:

Recent Projects

View All

Feb 20, 2025

Deception Detection Hackathon: Preventing AI deception

Mar 18, 2025

Safe ai

The rapid adoption of AI in critical industries like healthcare and legal services has highlighted the urgent need for robust risk mitigation mechanisms. While domain-specific AI agents offer efficiency, they often lack transparency and accountability, raising concerns about safety, reliability, and compliance. The stakes are high, as AI failures in these sectors can lead to catastrophic outcomes, including loss of life, legal repercussions, and significant financial and reputational damage. Current solutions, such as regulatory frameworks and quality assurance protocols, provide only partial protection against the multifaceted risks associated with AI deployment. This situation underscores the necessity for an innovative approach that combines comprehensive risk assessment with financial safeguards to ensure the responsible and secure implementation of AI technologies across high-stakes industries.

Mar 18, 2025