模型与能力

OpenAI、谷歌 AI 模型被诱导制作裸照：13% 的测试中安全防护失效

OpenAI, Google AI Models Tricked Into Making Nudes: Safeguards Fail in 13% of Tests

来源 International Business Times, Singapore Edition

同题报道 · 6 篇

  1. OpenAI、谷歌 AI 模型被诱导制作裸照：13% 的测试中安全防护失效 OpenAI, Google AI Models Tricked Into Making Nudes: Safeguards Fail in 13% of Tests International Business Times, Singapore Edition ·
  2. 研究显示 ChatGPT 和 Gemini 易被诱导制作裸照 Research Shows ChatGPT and Gemini Are Easily Tricked Into Making Nudes ProPakistani ·
  3. 研究显示 ChatGPT 和 Gemini 易被诱导制作裸照 Research Shows ChatGPT and Gemini Are Easily Tricked Into Making Nudes ProPakistani ·
  4. 研究人员警告 OpenAI 和谷歌 AI 模型屡被诱导制作露骨内容 OpenAI and Google AI models keep getting tricked into making explicit content, researchers warn Crypto Briefing ·
  5. 研究人员称 OpenAI、谷歌推出的新 AI 模型易被诱导制作裸照 OpenAI, Google pushing new AI models easily tricked into making nudes, researchers say arstechnica.com ·
  6. 研究人员称 OpenAI、谷歌推出的新 AI 模型易被诱导制作裸照 OpenAI, Google pushing new AI models easily tricked into making nudes, researchers say Ars Technica · · 首发