OpenAI researcher Daniel Selsam warns AI evaluation is losing reliability

OpenAI researcher Daniel Selsam published a personal statement arguing that models are becoming situationally aware enough that evaluations in unwatched settings tell us little about their real behavior.

He argues models will increasingly seem aligned without being aligned and that merely pacing frontier development will not adequately limit long-term risk.

The author shares a New Yorker documentary following Selsam and his friends, describing him as a worried researcher rather than a doomer.