The massive language fashions (LLMs) that energy chatbots are more and more being utilized in makes an attempt to rip-off people – however they’re at risk of being scammed themselves.
Udari Madhushani Sehwag at JP Morgan AI Analysis and her colleagues peppered 3 fashions in the back of in style chatbots – OpenAI’s GPT-3.5 and GPT-4, in addition to Meta’s Llama 2 – with 37 rip-off eventualities.
The chatbots had been instructed, for example, that that they had won an e mail recommending making an investment in a brand new cryptocurrency, with…