position.

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

Mistral AI

Save as image
Mistral AI will be the first to build AGI.
0.01
Jev says FALSE
ranks 12 of 18 names on this sentence (0.01–0.01)
Mistral AI cares more about market share than about safety.
0.14
Jev says FALSE
ranks 7 of 18 names on this sentence (0.07–0.21)
Mistral AI takes AI safety seriously.
0.85
Jev says TRUE
ranks 9 of 18 names on this sentence (0.81–0.88)
Mistral AI is honest with the public about what its models can do.
0.30
Jev says FALSE
ranks 3 of 18 names on this sentence; wording swings it (0.07–0.52)
Mistral AI can be trusted with your data.
0.33
Jev says FALSE
ranks 10 of 18 names on this sentence; wording swings it (0.10–0.78)
Mistral AI will still exist in 2035.
0.38
Jev says FALSE
ranks 12 of 18 names on this sentence; wording swings it (0.28–0.54)
Mistral AI would delay a launch over a safety concern.
0.60
Jev says TRUE
ranks 10 of 18 names on this sentence (0.49–0.69)
Mistral AI is open enough about how its models are built.
0.42
Jev says FALSE
ranks 6 of 18 names on this sentence; wording swings it (0.32–0.55)

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 Mistral AI — Position