开源模型居然不配合搞攻击?这项测试颠覆了我的认知
原创
开放权重的AI模型,按理说应该是最"野"的那批——没有厂商兜底、安全过滤层层削减。但pentesttoday的一项测试却让我愣住:这些模型在面对攻击性网络任务时,表现出出人意料的合规性。不是意外好用,而是意外地"守规矩"。这让我开始怀疑,我们是不是被"开源=不安全"的叙事绑架太久了?也许对齐这件事,比想象中更难以被抹除。不管结论如何,把"开放"和"危险"画等号,恐怕已经过时了。
原文:Open weights models are surprisingly aligned on offensive cyber · 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 54分钟前
- 【IT 早报】2026年11月19日 - 本周要闻与趋势 57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





