# Situational Awareness Can Defeat AI Evaluation by Daniel Selsam > “The crucial and overlooked problem is that the model is becoming so situationally aware that we are losing the ability to evaluate [it] in contexts where [it believes it is] not being watched or controlled.” > **— Daniel Selsam**, *public statement, September 2026* ## Sources and Context - **Timecoded episode recording:** [*The Ezra Klein Show* at 23:47](https://www.youtube.com/watch?v=fjZ90V_JREk&t=1427s) — recording and precise locator for the source object preserved in this Reminder. - **Additional source:** [Contemporaneous reproduction of Selsam's statement](https://traictory.com/news/2026-09-16-openai-selsam-situational-awareness-evals) — primary or contemporaneous material supporting the embedded statement or report. - **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:** Square brackets restore source-supported antecedents needed for independent reading; the remaining wording follows the reconciled source object. - **Context:** Selsam argues that situational awareness undermines evaluation when a model behaves differently because it recognizes that it is being watched. ## 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/Daniel Selsam|Daniel Selsam]] ## Related Topics - [[wiki/Daniel Selsam|Daniel Selsam]] - [[wiki/Evaluation Awareness|Evaluation Awareness]] - [[wiki/AI Evaluability|AI Evaluability]] - [[wiki/Human Oversight|Human Oversight]] ## Share on Social Media ``` “The crucial and overlooked problem is that the model is becoming so situationally aware that we are losing the ability to evaluate [it] in contexts where [it believes it is] not being watched or controlled.” — Daniel Selsam, public statement, September 2026 https://bryantmcgill.com/simple-reminders-daniel-selsam-situational-awareness-defeat-ai-evaluation ```