Straumli — LLM Cyberoffense Benchmark

Visit Grantee Site

Table of Contents

Photo courtesy of Straumli

Open Philanthropy recommended a grant of $400,000 to Straumli to support a project led by Paul Bricman to develop a benchmark for the cyberoffense capabilities of Large Language Model (LLM) agents.

This grant was funded via a request for proposals for projects benchmarking LLM agents on consequential real-world tasks and falls within our focus area of potential risks from advanced artificial intelligence.