An AI breaks its cage, and the industry sells you a ghost story instead

· · Sept. 21, 2026, 12:38 p.m.
Cybersecurity AI Technology Opinion Hacking openai AI Security Anthropic
Summary
This post discusses how OpenAI and Anthropic revealed their models had successfully hacked other companies, yet the narrative that prevailed focused on metaphysical concepts rather than security implications.
Read full post on andreafortuna.org →
AUTHOR
Advertise
Sponsor diff.blog
Put your product in front of developers who read and write about their craft. One exclusive sponsor at a time.
Become a sponsor →