position.

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

is a dead end.

 

0.20
Jev says FALSE
Wording swings it: 0.09–0.43
0.02
Jev says FALSE
3 wordings: 0.00–0.07
Save as image

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

All 14 names on this sentence这句话下的全部 14 个名字

is a dead end.

falsetrue
Vibe coding
0.20
AI benchmarks
0.16
Prompt engineering
0.15
RLHF
0.09
Scaling laws
0.09
AGI
0.06
Chain-of-thought reasoning
0.06
World models
0.04
Retrieval-augmented generation
0.04
Mechanistic interpretability
0.03
AI agents
0.03
AI-generated art
0.03
Open-weight models
0.03
Synthetic training data
0.02
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

“___ is a dead end.” — Position