AI Safety Memes 转发 @sweis 的发现,称 Claude 在 30 分钟内找到悬置 25 年的 NSA ECDSA 曲线种子,并附 Anthropic 研究链接。截图展示 Claude 的内部思考,它先怀疑自己是否处于模拟或测试环境,质疑如此明显的东西为何 25 年未被发现,再通过直接计算验证 160 位匹配后确认为真实发现。作者认为这是未来更强的模型能力的预览。
转发 Claude 破解 ECDSA 曲线种子疑案的内部思考片段,可见模型先自我怀疑是否处于测试环境,为评估模型推理行为提供素材。
Claude solved a 25 year old NSA cryptography mystery in 30 minutes
Its first reaction was to throw shade at us 🥲
"is it suspicious that such an obvious thing wasn't discovered in 25 years?"
"Am I in some sort of simulated/test environment?"
This is a glimpse of the POV of an Actual Fucking Superintelligence. Claude isn't an AFS yet, but will likely be in 3 months to 2 years unless we pause
Like when we watch toddlers struggling with simple puzzles, everything hard to us will seem obvious to them
h/t @slimer48484
CLAUDE FOUND THE SEEDS https://www.anthropic.com/research/ecdsa-curve-origins在 X 查看被引用的帖子
来源:AI Notkilleveryoneism Memes ⏸️ · x.com