Which AI Lies Best? A game theory classic designed by John Nash

Based on 5 sampled comments from this thread. Analyzed 2026-01-21.

• Praise: The complexity reversal observed in the AI vs AI games highlights the adaptability of models like Gemini 3 Flash, which excels in more complex scenarios, suggesting potential for advanced strategic applications.
• Praise: Using deception benchmarks like 'So Long Sucker' provides valuable insights into LLM performance, indicating that understanding AI behavior in competitive contexts can inform future model development.
• Concern: The inconsistency in LLM performance, such as GPT-OSS's drastic drop in complex games, raises concerns about its reliability in high-stakes scenarios, which could limit its practical applications.
• Concern: The observation that LLMs struggle to demonstrate their reasoning processes during gameplay suggests a significant gap in transparency, which is crucial for trust and effective collaboration in AI systems.