Large Language Models Fail to Predict Supreme Court Nuance and Unanimity
By Kelsey Dallas · SCOTUSblog · 2026-09-18

According to SCOTUSblog, recent research into AI performance shows that leading models like Gemini and Claude struggle to identify the specific legal questions that drive judicial outcomes. While attorneys are already using these tools for oral argument preparation, the systems f
According to SCOTUSblog, recent research into AI performance shows that leading models like Gemini and Claude struggle to identify the specific legal questions that drive judicial outcomes. While attorneys are already using these tools for oral argument preparation, the systems f