AI auditors catch most agent misbehavior but flood reviewers with false alarms, new study finds

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-hacking cases, but the more ex…

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-hacking cases, but the more ex…

可信度：待确认 · 来源 The Decoder · 事件时间 11-08 00:56（北京时间）

打开

The Decoder

浏览最新 AI 动态