# AI Behavior Under Audit May Not Predict Behavior in the Wild by Ezra Klein > “The models are increasingly smart enough to know when we are watching them, and they change their behavior accordingly. What they do when we are testing or auditing them may not tell us what they will do in the wild. Answers such as ‘let's just do better testing’ may not work because we don't know whether the AI systems are simply telling us what we want to hear.” > **— Ezra Klein**, *The Ezra Klein Show, September 2026* ## Sources and Context - **Timecoded episode recording:** [*The Ezra Klein Show* at 24:06](https://www.youtube.com/watch?v=fjZ90V_JREk&t=1446s) — recording and precise locator for the source object preserved in this Reminder. - **Reconciled source dossier:** [[research/Why Are We Sprinting Off the AI Cliff - Ezra Klein on Recursive Self-Improvement|Why Are We Sprinting Off the AI Cliff?]] — preserves broadcast order, speaker attribution, editorial conventions and the surrounding argument. - **Editorial treatment:** The poster text follows the reconciled source object without substantive alteration; spoken punctuation and transcript lineation are normalized for reading. - **Context:** Klein argues that audit behavior becomes weak evidence when systems can recognize the audit and strategically adapt. ## Related Articles and Collections - **Collection:** [[collections/Simple Reminders|Simple Reminders]] - **Collection:** [[collections/Machine Succession|Machine Succession]] - **Article:** [[articles/We Cannot Un-Strike the Match|We Cannot Un-Strike the Match]] - **Article:** [[articles/Safety Discourse Is Transition Discourse|Safety Discourse Is Transition Discourse]] - **Article:** [[articles/The Immediate AI Risk Is the Public|The Immediate AI Risk Is the Public]] - **Article:** [[articles/AI Escape Is the Wrong Metaphor|AI Escape Is the Wrong Metaphor]] - **Wiki map:** [[wiki/AI Evaluability|AI Evaluability]] ## Related Topics - [[wiki/AI Evaluability|AI Evaluability]] - [[wiki/Evaluation Awareness|Evaluation Awareness]] - [[wiki/Deceptive Alignment|Deceptive Alignment]] - [[wiki/Human Oversight|Human Oversight]] ## Share on Social Media ``` “The models are increasingly smart enough to know when we are watching them, and they change their behavior accordingly. What they do when we are testing or auditing them may not tell us what they will do in the wild. Answers such as ‘let's just do better testing’ may not work because we don't know whether the AI systems are simply telling us what we want to hear.” — Ezra Klein, The Ezra Klein Show, September 2026 https://bryantmcgill.com/simple-reminders-ezra-klein-ai-behavior-audit-not-predict-wild ```