The Decoder:AI auditors catch most agent misbehavior but flood reviewers with false alarms, new study fi…
原文摘要:AI models can often spot problematic behavior by other AI agents in logs, according to a study by Anthropic researcher Andy Hall. GPT-5 found about 98 percent of reward-ha 来源:The Decoder。建议继续查看原文,重点核对它影响的工具入口、成本、风险和真实使用场景。