Researchers have discovered a new way to hack AI assistants that uses a surprisingly old-school method: ASCII art. It turns out that chat-based large language models such as GPT-4 get so distracted trying to process these representations that they forget to enforce rules blocking harmful responses, such as those providing instructions for building bombs. ASCII art became popular in the 1970s, when the limitations of computers and printers prevented them fr
Tag: ai chatbots ars technica
Ai chatbots ars technica explained — what it is, how it works and what it costs. Below are 2 articles about ai chatbots ars technica on CheapToken News.
ASCII art elicits harmful responses from 5 major AI chatbots - Ars Technica
Google is quietly testing ads in AI chatbots - Ars Technica
The testing must have gone well because Google is now allowing more chatbot makers to sign up for AdSense. “AdSense for Search is available for websites that want to show relevant ads in their conversational AI experiences,” said a Google spokesperson. If people continue shifting to using AI chatbots to find information, this expansion of AdSense could help prop up profits. There’s no hint of advertising in Google’s own Gemini chatbot or AI Mode search, bu