logo
welcome
Live Science

Live Science

Scientists design new 'AGI benchmark' that indicates whether any future AI model could cause 'catastrophic harm'

Live Science
Summary
Nutrition label

82% Informative

"MLE-bench" is a compilation of 75 Kaggle tests, each one a challenge that tests machine learning engineering.

Each of the 75 tests holds real-world practical value, such as OpenVaccine and Vesuvius Challenge .

Any future AI that scores well on the tests may be considered powerful enough to be an AI that is smarter than humans.

VR Score

92

Informative language

96

Neutral language

74

Article tone

semi-formal

Language

English

Language complexity

62

Offensive language

not offensive

Hate speech

not hateful

Attention-grabbing headline

not detected

Known propaganda techniques

not detected

Time-value

long-living