Export
The link always opens the latest version of this page.
Ask an AI about it
Open in ChatGPTA new chat that reads this entry from the site Open in ClaudeThe same, in ClaudeShare the link instead of a file, and they will always see the latest version.
Files are a snapshot of today. The live page has anything newer.
Supreme Court oral argument simulation
AI technique to predict what a specific justice would ask given case facts, legal question, and argument transcript
A computational technique designed to predict questions that specific Supreme Court justices would pose during oral arguments, given case facts, legal questions, and argument transcripts.
Detection Capabilities
The technique demonstrates variable performance across different analytical dimensions:
Logical Fallacy Detection: Over 80% detection rate for logical fallacies in seven out of ten tested categories 1
Legal Issue Coverage: The approach can broadly address more than 60% of legal issues raised by actual SCOTUS justices 1, though best-performing models covered at most 41% of fine-grained legal issue details raised by real-world justices 1
Detection 3
- Able to broadly address more than 60% of legal issues raised by actual SCOTUS justices
- Best model covered at most 41% of fine-grained legal issue details raised by real-world justices
- Over 80% detection rate for logical fallacies in seven out of ten tested categories
Sources 1
- Facts & Fictions: Is AI-Assisted Oral Argument Preparation Worth the Hype? · Freedom to Tinker