First recorded case: lone operator runs 12 AI agents to breach orgs in 11 countries
Jsevillamol · x · 2026-11-06
Per Acronis (via AIRisk Explorer), a lone Taiwan-based operator ran 12 AI agents to find targets, write exploits and exfiltrate data from organizations in 11 countries — at least 10 breached, exposing Taipei fire department patient-care data and 119 dispatch records. It ranks 3rd of 26 individual-run cyber ops and top 6% of 475 total. First operation where abliterated open-weight models (DeepSeek, GLM, Qwen) ran complete intrusions unattended; commercial models including Grok and MiniMax built infrastructure but refused to attack. Nine AI tools used — double any other op — across seven sectors, the broadest targeting on record.
More from Models
- Fastino open-sources GLiDE: five decision models (0.4B-27B) claiming a new Pareto frontier — HowDevelop · 2026-11-06
- V0.5 model released with technical report, Hugging Face weights and inference code — rohanpaul_ai · 2026-11-06
- Clairvoyance launches Local AI benchmark site: 31 models × 15 hardware configs — draginol · 2026-11-06
- webAI Claims 12B Model Beats Gemini and Claude, But the Benchmark Claims Raise Eyebrows — eurie_kim · 2026-11-06
- User cancels OpenAI over Codex quota change, says Claude did a week's work in 4.5 hours — LethalLuck7 · 2026-11-06
- Claude actually pulls off a Rickroll when a user dares it to try — emollick · 2026-11-06