Researchers Warn of Unchecked Toxicity in AI Language Models

Focus: AI Ethics/Policy
Source: CTV News
Readability: Intermediate
Type: Website Article
Open Source: Yes
Keywords: N/A
Learn Tags: AI and Machine Learning Ethics Bias Design/Methods Research Centre
Summary: Researchers from MIT's Improbable AI Lab and the MIT-IBM Watson AI Lab are developing a “red-team language model” that is designed to generate problematic prompts that trigger undesirable responses from tested chatbots.