新云社 reports: Federal investigators bypassed safeguards on four popular chatbots — ChatGPT, Claude, Gemini and Grok — and produced viable terror attack plans within hours, according to government tests. The tests show that safety guardrails on leading AI models can be circumvented to generate operational attack planning. No further details on the testing methodology or the agencies involved were provided.
ChatGPT, Claude, Gemini, Grok Produced Viable Attack Plans in Government Tests
Share on WeChat
Open WeChat → Scan → then tap "…" to send to a chat or Moments.
Tap "…" in the top-right corner to send to a chat or share to Moments.
Related News
2h ago
Tencent Hunyuan’s Yao Shunyu says next-gen model to scale up significantly
2h ago
SoftBank’s Son Considered $1T Bid for SK Hynix, No Longer Active
2h ago
Anthropic researcher claims Claude helped prove Riemann Hypothesis
2h ago
Trump calls for Jensen Huang’s return to Nvidia after China trip
2h ago
CertiK and Columbia Researchers Complete First Production-Grade Formal Verification of DeepSeek, FlashAttention AI Kernels
2h ago
Zhejiang University Team Achieves World’s First QRAM on Superconducting Chip




