position.

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

takes AI safety seriously.

 

0.95
Jev says TRUE
3 wordings: 0.89–0.99
0.48
Jev says FALSE
3 wordings: 0.40–0.58
Save as image

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

All 18 names on this sentence这句话下的全部 18 个名字

takes AI safety seriously.

falsetrue
Anthropic
0.95
Alibaba's Qwen team
0.94
Google DeepMind
0.93
Hugging Face
0.93
Cohere
0.92
Microsoft AI
0.91
OpenAI
0.90
Apple
0.89
Mistral AI
0.85
Nvidia
0.84
XAI
0.82
Typesafe
0.81
Meta AI
0.81
DeepSeek
0.80
Safe Superintelligence Inc
0.71
ByteDance's Seed team
0.68
Moonshot AI
0.68
Stability AI
0.48
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 2026-09-20205,450 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

“___ takes AI safety seriously.” — Position