MIT Technology Review: Disputes over the reliability of AI refusal mechanisms
Start here
MIT Technology Review article discusses AI refusal mechanisms. The article points out that refusal has become a load-bearing wall of AI safety, but this mechanism is probabilistic in nature and destined to be difficult to make fully reliable. In 2021, Anthropic proposed that large language models should be helpful, honest, and harmless. Now models learn to refuse a large number of prompts through red team testing and AI-to-AI training, yet still retain knowledge for doing harm, with capability and benign intelligence growing in tandem. The article says some users are trying to use the most advanced AI to cultivate biological pathogens and build autonomous drone swarms, while the refusal boundary is secretly drawn by AI companies, and governments will also intervene.
Generated by AI from reports · Updated 3 days ago
Progress timeline
- MIT Technology ReviewMIT Technology Review：我们过度依赖 AI 的拒答能力
MIT Technology Review 刊文指出，拒答已成为 AI 安全的承重墙，但这一机制本质上是概率性的，注定难以完全可靠。Anthropic 2021 年提出大语言模型应有用、诚实且无害，如今模型经红队测试与 AI 互训学会拒绝大量提示词，却仍保留作恶知识，能力与善意智能同步增长。文章称部分用户正试图用最先进 AI 培育生物病原体、构建自主无人机蜂群，而拒答边界由 AI 公司秘密划定，政府也将介入。
Related discussion
Attention trend
New sources per day
- Oct 9New1 sources (1 outlets,0 accounts)
- Oct 10New0 sources (0 outlets,0 accounts)
- Oct 11New0 sources (0 outlets,0 accounts)
- Oct 12New0 sources (0 outlets,0 accounts)