Monday, March 17, 2025

AI models fall for the same scams that we do

Date:


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

Share post:

spot_img

Popular

More like this
Related

Asus jacks up prices on Nvidia and AMD GPUs

Graphics card prices are shooting up… and not...

Roblox unveils Roblox Cube GenAI and other game dev tools for GDC

Roblox introduced its Roblox Cube AI tools, the...

We Talked to the Inventors of the “Tamagotchi” Vape That Dies If You Stop Puffing

Image by Rebecca Xun / Lucia CamachoEarlier this...