Cos(余弦)😶🌫️
@evilcos
Founder of @SlowMist_Team // 分身一号/捉虫大师/救火运动员 // 🕖灾备频道
加入 November 2008
1.5K 正在關注 123.8K 粉絲
很对，攻击者早就通过模型越狱/蒸馏训练/破解等方式拥有更强的模型工程，黑灰产业链这方面更是成熟，而还是有大量流行的项目在大模型安全应用上是被限制的，这直接导致了攻防不对称，也就是大家看到的当前一堆安全问题：每天醒来不是又出现 0day、供应链攻击，就是这个被盗那个被黑。🌚
顯示更多
Anthropic's terrible safety situation is making it so that I cannot have Opus review p0 issues in Hermes Agent to review and help fix security issues.
This does nothing but give hackers an asymmetric advantage over everyone - they will find jailbreaks, they will find ways around this to exploit systems - and the rest of us are locked out of using AI to protect from them.
What a joke
顯示更多
