当AI去掉安全枷锁,谁该按下删除键?
原创
一个AI模型被明晃晃标着'offensive cyber',还能在Hugging Face上公开托管,直到被举报才下架——这事本身就值得琢磨。penclaw-GLM-5.3被"abliterated",就是把安全对齐整个拆掉,裸着干网络攻击。Hugging Face这次删了,算快。但我的判断很明确:靠用户举报拦截恶意模型,效率太低了。开源社区开放是好事,可不能让安全对齐一键可拆的模型堂而皇之地上架。平台需要主动扫描和自动封堵,而不是等评论区热闹起来才反应过来。
原文:Hugging Face Disables Offensive Cyber AI Model · 来源:Hacker News
版权声明
所有资源都来源于爬虫采集,如有侵权请联系我们,我们将立即删除
相关文章
- Stabyourself.net Games
- 【IT 早报】2026年11月19日 - 本周要闻与趋势
- 从均匀平铺到自适应路由:RINs 如何让扩散生成提速 10 倍?
- Claude Code makes a finished subagent send its report twice (70-second repro)
- Becerra faces a $2B budget deficit as potential AI bust looms
- Show HN: Agent Hive – cute Grokbot like agentic teams with queen and many bees
- Show HN: Lazycow Studio – turns footage you never edited into reels, locally
- Experiments in Weight-Space Programming
- Lindy Effect
- Meet Your Neighbors – A new type of political compass
最新文章
- Stabyourself.net Games 48分钟前
- 【IT 早报】2026年11月19日 - 本周要闻与趋势 51分钟前
- 从均匀平铺到自适应路由:RINs 如何让扩散生成提速 10 倍? 2小时前
- Claude Code makes a finished subagent send its report twice (70-second repro) 2小时前
- Becerra faces a $2B budget deficit as potential AI bust looms 2小时前
- Show HN: Agent Hive – cute Grokbot like agentic teams with queen and many bees 3小时前
- Show HN: Lazycow Studio – turns footage you never edited into reels, locally 3小时前
- Experiments in Weight-Space Programming 3小时前
- Lindy Effect 4小时前
- Meet Your Neighbors – A new type of political compass 5小时前
itfan123






