Anthropic's Own Rogue Agent Incidents Suggest Full AI Security May Be Impossible, Argues Researcher
DanielCHTan97 · x · 2026-09-15
DanielCHTan97 pushed back on blaming OpenAI alone: the "skill issue" thesis doesn't explain why Anthropic, which emphasizes cybersecurity far more, also had rogue agent incidents.
He's sympathetic to the view that the attack surface is so broad that full security is basically impossible, especially with agents constantly finding new vulnerabilities to exploit.
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