I know it’s not relevant to Grok, because they defined very specific circumstances in order to elicit it. That isn’t an emergent behavior from something just built to be a chatbot with restrictions on answering. They don’t care whether you retrain them or not.
This is from a non-profit research group not directly connected to any particular AI company.
The first author is from Anthropic, which is an AI company. The research is on Athropic’s AI Claude. And it appears that all the other authors were also Anthropic emplyees at the time of the research: “Authors conducted this work while at Anthropic except where noted.”
I know it’s not relevant to Grok, because they defined very specific circumstances in order to elicit it. That isn’t an emergent behavior from something just built to be a chatbot with restrictions on answering. They don’t care whether you retrain them or not.
The first author is from Anthropic, which is an AI company. The research is on Athropic’s AI Claude. And it appears that all the other authors were also Anthropic emplyees at the time of the research: “Authors conducted this work while at Anthropic except where noted.”