Author

Zoe De Simone

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Apr 2026

Alignment has a Fantasia Problem

It is argued that Fantasia interactions demand a rethinking of alignment research, where AI systems optimize how cognitive responsibility is allocated within an interaction, and highlights gaps in state-of-the-art alignment methods.

Nathanael Jo, Zoe De Simone, Mitchell Gordon et al. · arXiv.org · 0 citations

#artificial intelligence Preprint Sep 2026

Why Better Models Can Create Riskier Systems: Evidence from LLM Agents in Financial Markets

Large language models (LLMs) are being deployed at scale in consequential real-world systems, from financial markets to content moderation to hiring. We show that improving individual model capability can degrade rather than improve system-level outcomes. We hypothesize that shared training and architectures can lead m...

Jillian Ross, Eric C. So, Zoe De Simone et al. · 0 citations