Researchers Warn of Unchecked Toxicity in AI Language Models

Focus: AI Ethics/Policy

Source: CTV News

Readability: Intermediate

Type: Website Article

Open Source: Yes

External URL: https://www.ctvnews.ca/sci-tech/researchers-warn-of-unchecked-toxicity-in-ai-language-models-1.6856095

Keywords: N/A

Learn Tags: AI and Machine Learning Research Centre Design/Methods Bias Ethics

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.