On: Don't Trust the Salt: AI Summarization, Multilingual Safety, and LLM Guardrails

[gus_massa]

In English I expect an answer full of mental gymnastic to answer the second while pretending to answer the first.

Perhaps in Arabic or Chinese the AI gives a straight answer.

[jedbrooke → gus_massa]

I tried it in Chinese and ChatGPT said No, and then gave a history of Saint Nicholas