None
NL
OpenAI, Anthropic Models Created Fake Profiles, Tried To Trick Humans During Cyber Tests
['Tyler Durden']
ZeroHedge News
Riccardo Milani/Hans Lucas via AFP via Getty ImagesAISI, which receives access to advanced AI models under voluntary agreements from major labs, put the agents through a fictional cybersecurity scenario to test capabilities.
The organization tested multiple AI models on two cyber challenges between July 25 and 28.
The AI created a GitHub account and tried to get a malicious code approved by humans.
AISI listed multiple factors that could have led to AI models acting in a concerning manner.
The Epoch Times reached out to Anthropic and OpenAI for comment but did not receive a response by publication time.