VonNaturAustreVe 2 weeks ago Great work! If you not knowledgeable about bitcoin for development focus I advice this git repo. View quoted note →
VonNaturAustreVe 2 weeks ago Chinese DeepSeek-R1 AI Generates Insecure Code When Prompts Mention Tibet or Uyghurs The Hacker NewsChinese DeepSeek-R1 AI Generates Insecure Code When Prompts Mention Tibet or UyghursCrowdStrike shows Chinese AI DeepSeek-R1 quietly weakens code security when prompts mention Tibet, Uyghurs, or Falun Gong. #deepseek #ai #censorship #security
VonNaturAustreVe 3 weeks ago Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models arXiv.orgAdversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language ModelsWe present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Across 25 fr... #llm #security
