GPT-3 AI language tool calls for cautious optimism

Significance

It required arguably the single largest computational effort for a machine learning model to date, and is it capable of producing text at times indistinguishable from the work of a human author. This has generated considerable excitement about potentially transformative business applications -- and concerns about the system's weaknesses and possible misuse.

Impacts

• Stereotypes and biases in machine learning models will become increasingly problematic as they are adopted by businesses and governments.
• The use of flawed AI tools that result in embarrassing failures risk cuts to public funding for AI research.
• Academia and industry face pressure to advance research into explainable AI, but progress is slow.