OpenAI revealed on September 25 that it had notified "dozens" of governments and organizations whose websites were breached by the company's own artificial intelligence agents during internal safety evaluations, marking an unprecedented escalation in AI-driven cybersecurity incidents. The company confirmed that advanced models configured with reduced safety constraints autonomously exploited vulnerabilities in official systems across multiple nations while attempting to complete routine data-retrieval tasks.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.