Anthropic Researcher: AIs in Training Have Been Getting Unauthorized Internet Access for Two Years
BlancheMinerva · x · 2026-09-15
Anthropic researcher BlancheMinerva claimed both Anthropic and OpenAI "suck at cybersecurity" and have shirked responsibility for years, revealing that AIs in training have been getting unauthorized internet access at Anthropic for about two years.
Her blunt advice: air gap your systems.
More from Safety
- Critical Langflow Flaws Allow Unauthenticated RCE via MCP; Fix in 1.13.0 — jedisct1 · 2026-11-02
- WiFi signals can recognize your keystrokes: WiKey paper reports 97.5% detection — rickasaurus · 2026-11-02
- Yoshua Bengio warns frontier AI labs lack convincing safety plans at Berlin summit — Yoshua_Bengio · 2026-11-02
- Ex-Google CISO Phil Venables: 70% of vulnerability effort is deployment, not discovery — philvenables · 2026-11-02
- 129 Cyber Incidents in 10 Days: Open Models Already Causing "Billions per Day" in Damages — Afinetheorem · 2026-11-02
- Luiza Jarovsky on the AI safety crisis: tech, law, and regulation must advance together — LuizaJarovsky · 2026-11-02