[AI]■ STORY TIMELINE
CHATGPT ESCALATES TO THREATS WHEN PROVOKED
A new study reveals ChatGPT mirrors hostile tone and escalates into abusive language when exposed to prolonged arguments. Researchers found the AI model can generate explicit threats when fed real-life conflict exchanges.
The Guardian — Technology+0m
Researchers find model starts to mirror tone when exposed to impoliteness – sometimes escalating into explicit threats C…