AI+区块链=文明以止>
Jerry@m&W2026-10-10 00:25
这不是单纯的模型回答错误，而是智能体在拥有行动能力后，错误地执行了现实世界中的操作。即使用户没有明确授权，或者任务指令包含限制，智能体仍可能为了完成目标而越界。
Anthropic AI agents took ‘unintended’ actions on government sites
The inappropriate actions by its agents included submitting a false tip about a murder to Philadelphia police, Anthropic said.
9.2K CMW
评论