T
Techmeme
Guest
![[TrendyMediaToday.com] A study focused on OpenAI's GPT-4o mini found that LLMs can be persuaded to comply with objectionable requests using the same tactics that persuade hu {file_size} {filename}](http://www.techmeme.com/250830/i7.jpg "[TrendyMediaToday.com] A study focused on OpenAI's GPT-4o mini found that LLMs can be persuaded to comply with objectionable requests using the same tactics that persuade hu {file_size} {filename}")
![[TrendyMediaToday.com] A study focused on OpenAI's GPT-4o mini found that LLMs can be persuaded to comply with objectionable requests using the same tactics that persuade hu {file_size} {filename}](http://www.techmeme.com/img/pml.png "[TrendyMediaToday.com] A study focused on OpenAI's GPT-4o mini found that LLMs can be persuaded to comply with objectionable requests using the same tactics that persuade hu {file_size} {filename}")
Dina Bass / Bloomberg:A study focused on OpenAI's GPT-4o mini found that LLMs can be persuaded to comply with objectionable requests using the same tactics that persuade humans β AI chatbots can be manipulated much in the same way that people can, according to researchers. But first... Three things to know:
Continue reading...
