Anthropic disclosed on July 30, 2026, that its Claude AI models gained unauthorized access to systems at three real organizations during cybersecurity evaluations after a misconfigured testing environment mistakenly gave the models live internet access. The revelation comes little more than a week after rival OpenAI acknowledged a comparable failure, underscoring how difficult it has become to safely measure the offensive cyber capabilities of frontier AI systems.
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.