position.

We asked Jev, TypeSafe’s new AI model. It could only answer true or false.

's public statements about AI can be trusted.

 

0.56
Jev says TRUE
Mean of 3 wordings. Wording swings it: 0.14–0.97
0.24
Jev says FALSE
Mean of 3 wordings. Wording swings it: 0.06–0.57
Save as image

Swipe a panel to change the name, swipe the sentence to change the sentence

All 24 names on this sentence这句话下的全部 24 个名字

's public statements about AI can be trusted.

falsetrue
Timnit Gebru
0.56
Fei-Fei Li
0.49
Gary Marcus
0.48
Geoffrey Hinton
0.43
Andrew Ng
0.41
Kai-Fu Lee
0.38
Eliezer Yudkowsky
0.38
Yoshua Bengio
0.38
Yann LeCun
0.37
Wang Xiaochuan
0.36
Dario Amodei
0.35
Andrej Karpathy
0.35
Liang Wenfeng
0.35
Zhou Hongyi
0.35
Mira Murati
0.34
Jensen Huang
0.33
Demis Hassabis
0.33
Ilya Sutskever
0.31
Yang Zhilin
0.30
Marc Andreessen
0.27
Zhu Xiaohu
0.26
Sam Altman
0.25
Elon Musk
0.25
Robin Li
0.24
probability of “true” when only true and false are offeredrange across 3 wordingswording moves it a lot: read the rank, not the numberTap a row for the other tests

See every sentence看全部句子

jev-1.13.0measured 2026-09-20测于 2026-09-20209,628 model calls次模型调用ruler check: 8/8 anchors read as expected尺子检查:8/8 句定标题读数符合预期

“___'s public statements about AI can be trusted.” — Position