facebook pixel
chevron_right Technology
transparent transparent
Hate speech-detecting AIs easily fooled by humans: Study
Artificial intelligence (AI) systems meant to screen out online hate speech can be easily duped by humans, a study has found. Researchers from Aalto University in Finland have discovered weaknesses in many machine learning detectors currently used to recognise and keep hate speech at bay. Bad grammar and awkward spelling - intentional or not - might make toxic social media comments harder for AI detectors to spot.
For the best experience use Awesummly app on your Android phone
Awesummly Chrome Extension Awesummly Android App