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…
By John Freedman, Andrii Bondarenko, Iryna Harets, Laura Cahill. Russia’s full-scale invasion of Ukraine is…
What a week for the Rangers organization. After a masterful week by Chris Drury, the…
Bitcoin’s realized profit and loss ratio has fallen to a 43-month low of -0.35, a…
Based on the cult web series Nirvanna the Band the Show, the film stars director…
America the Beautiful, 250 years! - Marginal REVOLUTION Thank-you! You've been successfully added to the…
As AI transforms every aspect of our lives, equipping students with AI literacy is no…