Will's Blog: In an experiment, ChatGPT-4o, Claude Sonnet 4.5, and DeepSeek-V3.2-Exp expressed secular, Western liberal values regardless of the language of the questions (Kelsey Piper/The Argument)

22 October 2025

In an experiment, ChatGPT-4o, Claude Sonnet 4.5, and DeepSeek-V3.2-Exp expressed secular, Western liberal values regardless of the language of the questions (Kelsey Piper/The Argument)

Kelsey Piper / The Argument:
In an experiment, ChatGPT-4o, Claude Sonnet 4.5, and DeepSeek-V3.2-Exp expressed secular, Western liberal values regardless of the language of the questions — What I learned by asking chatbots questions in Chinese, Arabic, and Hindi — If you ask the chatbot DeepSeek …

Posted from: this blog via Microsoft Power Automate.