Press Enter to search · ESC to close

AI × Crypto

ChatGPT, Claude, Gemini, Grok Produced Viable Attack Plans in Government Tests

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.

Share

Related News

新云社 share card
Long-press image above → Save to Photos / Share
Pitch us Feedback