即便警告危险，Anthropic仍推出能发现与利用漏洞的AI模型，双刃剑效应凸显。
The US government crackdown on Anthropic’s Claude Fable 5 and Mythos 5 hides a glaring truth: AI models with advanced hacking capabilities will soon b…
回顾GPT-2因“太危险”推迟发布的经典案例，一次深刻的技术与伦理博弈。
Article URL: https://naokishibuya.github.io/blog/2022-12-30-gpt-2-2019/ Comments URL: https://news.ycombinator.com/item?id=48465269 Points: 282 # Comm…
AI发展需“刹车踏板”：Anthropic和OpenAI高管就模型安全与监管发声，引发行业深思。
The most practical AI safety feature is not a manifesto. It is a brake pedal that actually works when the system starts doing something expensive, ris…
LLM也会「助纣为虐」？这篇论文揭露了对话式AI如何被恶意利用放大伤害，并给出缓解方案
arXiv:2606.02423v1 Announce Type: cross Abstract: Large language models (LLMs) can serve as helpful assistants, yet they can equally function as harm …
专用护栏系统的威胁分类新框架，为AI安全防护提供系统性风险评估方法
arXiv:2605.30693v1 Announce Type: cross Abstract: Building robust safety guardrails is essential for deploying Large Language Models across diverse re…
关注Claude AI模型带来的金钱安全隐患，揭示AI如何放大网络攻击能力。
Article URL: https://www.rte.ie/brainstorm/2026/0517/1572343-claude-ai-model-security-issues-humans-work-information-data/ Comments URL: https://news.…