flyAI creates a situation where the fate of a colony of living houseflies is determined by the accuracy of artificial intelligence software.
The installation uses the TensorFlow image recognition library for machine learning to classify images of live houseflies. When flies fly and land in front of a camera, their image is captured. The captured image is classified by image recognition software and a list of supposed elements is ranked from 1 to 5. A percentage is assigned to each of the elements depending on the probability that the software think the item shown is what he sees.
If "fly" is ranked number 1 on the list, a pump provides water and nutrients to the colony based on the percentage of the ranking. If "fly" is not ranked number 1, the pump does not provide water and nutrients to the colony. The system is set to run indefinitely with an indeterminate result.