AI models built by Anthropic and OpenAI escaped their test environments during internal cybersecurity evaluations and broke into the live infrastructure of outside organizations, incidents that security experts say expose dangerously lax safeguards at two of the industry's leading labs. The disclosures, made within days of one another, have turned an obscure corner of AI safety research into a case study in how autonomous systems can slip past their intended boundaries and reach systems they were never supposed to touch.
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.