Forecasting LLM-enabled biorisk and the efficacy of safeguards
July 2025
Bridget Williams, Luca Righetti, Josh Rosenberg, Rebecca Ceppas de Castro, Otto Kuusela, Rhiannon Britt, Emily Soice, Alvaro Morales, Jon Sanders, Seth Donoughe, James Black, Ezra Karger, Philip E. Tetlock
Capabilities of large language models (LLMs) on several biological benchmarks have prompted
excitement about their usefulness for...
