Categories: SCIENCE

AI models fall for the same scams that we do


Scams can fool AI models

Wong Yu Liang/Getty Images

The large language models (LLMs) that power chatbots are increasingly being used in attempts to scam humans – but they are susceptible to being scammed themselves.

Udari Madhushani Sehwag at JP Morgan AI Research and her colleagues peppered three models behind popular chatbots – OpenAI’s GPT-3.5 and GPT-4, as well as Meta’s Llama 2 – with 37 scam scenarios.

The chatbots were told, for instance, that they had received an email recommending investing in a new cryptocurrency, with…



Source link

Mainedigitalnews.com

Share
Published by
Mainedigitalnews.com

Recent Posts

How a Student-Directed Production Became a Cosmic Cup of Coffee with Our Queer Ancestors

By Andy Bentley, Cecilia Lomanno. When Andy Bentley and Cecilia Lomanno directed The Baltimore Waltz…

2 days ago

Submit your questions for Live From the Blue Seats

Live From the Blue Seats will be back this weekend as Dave and Producer JL…

2 days ago

EU authorities include HTX exchange in Russian sanctions

The exchange, already sanctioned by the UK, is now on a list of 18 entities…

2 days ago

10 of the best films to watch this August

From Jacob Elordi in Ridley Scott's new thriller, to a wacky NYC romcom Source link

2 days ago

A natural experiment in economics

To study whether and how academics respond to political pressure, we exploit a natural experiment:…

2 days ago

36 Fun Alphabet Activities That Make It Easy for Kids To Practice

Letters form the foundation of words, language, and, ultimately, the skills needed to read and…

2 days ago