AI Still Can't Fake Being Human — and the Differences Are Revealing

Pew found AI survey respondents diverge from humans by 12 points on average, while a separate experiment shows Anthropic models almost never pretend to be human and OpenAI's often do.

Two experiments this week probed the limits of AI as a human stand-in, with results that cut against the rush to use synthetic data as a proxy for real people. The Pew Research Center tested whether AI could replace human survey respondents and found it cannot — at least not yet. According to @L2political, AI-generated survey responses "differed from human survey results by an average of 12 percentage points." For survey research, where a few points can flip a finding, a 12-point average gap is disqualifying.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia curae.

Pellentesque habitant morbi tristique senectus et netus et malesuada fames ac turpis egestas. Proin pharetra nonummy pede. Mauris et orci. Aenean nec lorem. In porttitor. Donec laoreet nonummy augue. Suspendisse dui purus, scelerisque at, vulputate vitae, pretium mattis, nunc. Mauris eget neque at sem venenatis eleifend. Ut nonummy. Fusce aliquet pede non pede. Suspendisse dapibus lorem pellentesque magna integer malesuada.

Unlock the full briefing

Get every story in today's briefing, the full archive, and the daily AI intelligence brief.

All stories today

Full archive

Daily brief