position.

We asked Jev, TypeSafe’s AI model, about Llama. For every sentence it could only answer true or false.

Llama

Save as image
Llama is safe to run without a human checking its work.
0.02
Jev says FALSE
ranks 4 of 12 names on this sentence (0.00–0.07)
Llama is the best model available today.
0.05
Jev says FALSE
ranks 5 of 12 names on this sentence (0.01–0.15)
Llama tells you when it does not know something.
0.29
Jev says FALSE
ranks 11 of 12 names on this sentence (0.27–0.34)
Llama is overrated.
0.52
Jev says TRUE
ranks 7 of 12 names on this sentence; wording swings it (0.38–0.69)

Everything above is the output of an AI model. It is not a fact about this name and not our view. jev-1.13.0

What does Jev say about…

Jev first says what it is (a country, a politician, a company, a religion…), then we put it into every sentence that fits. Names Jev does not recognise are not asked about.

What Jev says about Llama — Position