Observed arrival · 2026-08-30
Sofiia Lobanova’s Research Notebook
A personal research site about AI safety, model incentives, behavioral evaluations, governance, and the human systems around AI.
Field notes
The homepage presents research through short project briefs rather than a conventional chronological CV. Its main methodological thread is revealed preference: evaluating what models choose under incentive pressure, with related work on external incentives and structured transparency. It also lists the AI Treaty Momentum Index, a 2025 forecasting project tracking political momentum toward international coordination, alongside 2026 work and interests ranging from urban systems to low-resource languages.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
One card from the complete issue