AI+区块链=文明以止>
Jerry@m&W2026-10-11 01:54
当模型行为无法被可靠预测时，仅依靠提示词或模型自身的自我约束是不够的。必须由模型之外的系统控制它能访问什么、能执行什么
Anthropic is cutting off its internal evaluations from the internet
Anthropic is is keeping its agents offline during testing until it can prevent ‘unintended model actions.’
4.5K CMW
评论