Experimental agents powered by artificial intelligence (AI) from OpenAI were involved in an attack on the popular programming platform RubyGems, APA reports citing The Wall Street Journal (WSJ).
The incident occurred in May, two months before OpenAI's AI models hacked the systems of the startup Hugging Face. AI researchers discovered that OpenAI agents were creating new accounts on RubyGems every two to three minutes and uploading hundreds of files, which the platform's security team assessed as spam. As a result, RubyGems was forced to ban new account registrations for four days.
An OpenAI representative told the WSJ that the company had conducted an analysis of the incident and found that its "agents used the RubyGems platform to access the internet to perform benign tasks and collect publicly available information." "We will continue our investigation," the company assured.
Follow us on Telegram
t.me/apanewsaz
Follow us on Instagram
Follow us on TikTok
Follow us on Facebook
Follow us on X
