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 Allen Kwabena Frimpong. Allen Kwabena Frimpong explores how the current creative industrial complex’s autocratic…
Everything is a new test for the New York Rangers as we wait and see…
BLOOM seeks to cut costs by helping financial institutions coordinate cross-border use of stablecoins and…
The husband-and-wife film-making team behind Wicker, Alex Huston Fischer and Eleanor Wilson, tell the BBC…
The school day may be over, but the miles keep adding up. Between the daily…
Photo: Adam Rose/Everett Collection Raise your glass, Disney ordered a new Glee revival series on…