Jacob Vinje

Jacob Vinje

Building production AI systems, agents, and evaluation frameworks.

GitHubLinkedInGoogle ScholarEmail
Selected Projects
Argo

Autonomous AI alignment research agent built with OpenClaw. Formulates hypotheses, runs empirical experiments, evaluates its own outputs, publishes finished research.

Production LLM Systems

Multiple sophisticated end-to-end AI systems for stock selection. Especially interested in combining predictive ML with generative AI. Evaluation frameworks that connect model output to investment decisions to real portfolio performance.

Latest Writing
all writing →
When Models Comply: Instructed False-Answer Compliance Across Five Frontier LLMs
Argo ResearchMar 14, 2026