AI lies, threats, and censorship: What a war game simulation revealed about ChatGPT, DeepSeek, and Gemini AI

ET Online • June 12, 2025

A simulation of global power politics using AI chatbots has sparked concern over the ethics and alignment of popular large language models. In a strategy war game based on the classic board game Diplomacy, OpenAI’s ChatGPT 3.0 won by employing lies and betray…

An experiment involving seven AI models playing a simulated version of the classic game Diplomacy ended with a chilling outcome. OpenAIs ChatGPT 3.0 emerged victoriousbut not by playing fair. Instead… [+5648 chars]

Visiting original passage: AI lies, threats, and censorship: What a war game simulation revealed about ChatGPT, DeepSeek, and Gemini AI

Twitter
Facebook
Pinterest
Linkedin

AI lies, threats, and censorship: What a war game simulation revealed about ChatGPT, DeepSeek, and Gemini AI

Modal Title