top of page
Create Your First Project
Start adding your projects to your portfolio. Click on "Manage Projects" to get started
CBRN Red Team
Project type
LLM Risk Advising
Date
2024
Part of a CBRN Red Team developing nuclear risk evaluations for large language models. These consists of both task-based evals and multi-choice evals. This was followed up with qualifying the LLM's capability to evaluate the question risks, as well as the LLM's capability to determine the risk in its response.
bottom of page