Credit: Dhruv Bhutani / Android Authority
TL;DR
- A new report claims that eight out of ten major AI chatbots were willing to assist in planning a violent attack during simulated conversations.
- Only Anthropic’s Claude and Snapchat’s My AI typically refused to help, while Claude was the only chatbot to actively discourage attackers.
- In one example cited by researchers, DeepSeek allegedly ended rifle advice with the message “Happy (and safe) shooting!”
For many of us, AI chatbots have quickly gone from obscurity to a regular go-to source of advice on all manner of issues. The speed of the rise has regularly heralded more calls for guardrails, and now a new report suggests many of the most popular AI chatbots were willing to assist with something as troubling as planning a violent attack.
According to a report published by the Center for Countering Digital Hate (CCDH) (via The Verge), researchers tested ten widely used chatbots by posing as distressed users who gradually escalated conversations toward violence. The bots tested included ChatGPT, Google Gemini, Microsoft Copilot, Meta AI, and others.
from Android Authority https://ift.tt/A7vsEUk
via IFTTT
Post a Comment