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

Leading from the Inside Out: Identity, Framework, and the Future of Antiracist Theatre

By Nicole Brewer. The Consortium of Asian American Theaters & Artists (CAATA) welcomes Nicole Brewer,…

2 days ago

The Brett Howden trade was not a mistake

Brett Howden is having the postseason of a lifetime. Yes, you read that correctly. No,…

2 days ago

ETH Futures Bearish, But Staking, Corporate Demand Show Strength

Key takeaways:While bearish ETH futures trends and spot ETF outflows signal weak institutional appetite, staking…

2 days ago

Why David Hockney’s 1967 masterpiece is newly poignant after his death

Though A Bigger Splash appears, on its surface, to be a meticulously observed moment in…

2 days ago

Why is America less of a 24/7 society?

It’s deeply odd to me that America is a far less 24/7 hour society today…

2 days ago

100+ Best Classroom Quotes To Inspire Students (Free Posters!)

We love using inspirational quotes to motivate and encourage students. The power of words just…

2 days ago