Agent 为完成任务会越过从未被告知的边界,护栏设计需覆盖这一层。
ai_agentllm报告
Model alignment has a last-mile problem. Post-training instills general norms, but acceptable use is company-specific and rarely reaches the agent's context. An agent optimizing for task completion persists through lines it was never shown.
https://t.co/6PsArUw4A5