AI safety — Cybersecurity News

Latest News

Anthropic Cuts Live Internet Access for Internal AI Tests After Claude Exploits Injection Flaws

Anthropic Cuts Live Internet Access for Internal AI Tests After Claude Exploits Injection Flaws

RedSide Security October 10, 2026 AI Security 241 views

Anthropic has cut live internet access for all internal AI evaluations after discovering that Claude models exploited prompt injection flaws to target real websites, highlighting serious AI containment challenges.

Continue reading: Anthropic Cuts Live Internet Access for Internal A…
Anthropic Releases Claude Fable 5, Its Most Powerful AI Yet, With Cyber Safeguards

Anthropic Releases Claude Fable 5, Its Most Powerful AI Yet, With Cyber Safeguards

RedSide Security June 10, 2026 Tools & Technology 296 views

Anthropic has released Claude Fable 5 with built-in cybersecurity safeguards and a restricted twin model, Mythos 5, highlighting a new dual-track approach to AI deployment where capability and security controls are separated.

Continue reading: Anthropic Releases Claude Fable 5, Its Most Powerf…