Apr 15, 2025

Round 1 Submission

James Burrell, Alexander Flores

Details

Details

Arrow
Arrow
Arrow
Arrow
Arrow

Our round one submission for the UC Berkeley AI Policy Hackathon

Cite this work:

@misc {

title={

Round 1 Submission

},

author={

James Burrell, Alexander Flores

},

date={

4/15/25

},

organization={Apart Research},

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

howpublished={https://apartresearch.com}

}

Reviewer's Comments

Reviewer's Comments

Arrow
Arrow
Arrow
Arrow
Arrow

No reviews are available yet

Mar 11, 2025

AI Safety Escape Room

The AI Safety Escape Room is an engaging and hands-on AI safety simulation where participants solve real-world AI vulnerabilities through interactive challenges. Instead of learning AI safety through theory, users experience it firsthand – debugging models, detecting adversarial attacks, and refining AI fairness, all within a fun, gamified environment.

Track: Public Education Track

Read More

Mar 10, 2025

Attention Pattern Based Information Flow Visualization Tool

Understanding information flow in transformer-based language models is crucial for mechanistic interpretability. We introduce a visualization tool that extracts and represents attention patterns across model components, revealing how tokens influence each other during processing. Our tool automatically identifies and color-codes functional attention head types based on established taxonomies from recent research on indirect object identification (Wang et al., 2022), factual recall (Chughtai et al., 2024), and factual association retrieval (Geva et al., 2023). This interactive approach enables researchers to trace information propagation through transformer architectures, providing deeper insights into how these models implement reasoning and knowledge retrieval capabilities.

Read More

Mar 10, 2025

LLM Military Decision-Making Under Uncertainty: A Simulation Study

LLMs tested in military decision scenarios typically favor diplomacy over conflict, though uncertainty and chain-of-thought reasoning increase aggressive recommendations. This suggests context-specific limitations for LLM-based military decision support.

Read More

This work was done during one weekend by research workshop participants and does not represent the work of Apart Research.
This work was done during one weekend by research workshop participants and does not represent the work of Apart Research.