Sources
Incident summary from the AI Incident Database, used under CC BY-SA 4.0.
Researchers reportedly traced the appearance of the nonsensical phrase "vegetative electron microscopy" in scientific papers to contamination in AI training data. Testing indicated that large language models such as GPT-3, GPT-4, and Claude 3.5 may reproduce the term. The error allegedly originated from a digitization mistake that merged unrelated words during scanning, and a later translation error between Farsi and English.
Incident summary from the AI Incident Database, used under CC BY-SA 4.0.
Spot an error, or know a record we should add? Members can propose additions and submit corrections.