Looking for insights into AI generation biases I used GPT-3 to define a word that has never been written before: Steradects.
Phrasing the definition as “Steradects is” provides an endless stream of false but credible explanations. Instead, when asked “Steradects is not” the LLM can recognize the word as non-existent. The installation presents both sets of answers from opposite viewing points, inviting the visitor to choose what they want to know.

MA research & design project
Design Academy Eindhoven
Eindhoven, NL