lechmazur/deception

Benchmark evaluating LLMs on their ability to create and resist disinformation. Includes comprehensive testing across major models (Claude, GPT-4, Gemini, Llama, etc.) with standardized evaluation metrics.

7 best points · 1 comments · 1 Hacker News post · 36 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: LLM Deceptiveness and Gullibility Benchmark (7 points, 1 comments, by zone411, 2024-10-22)