The Authors Guild has published updated best practices for writers navigating the use of generative AI in their profession, originally released in February 2024 and refreshed as of May 2026. The guidelines emphasize that authorship means the words, thoughts, and creativity are genuinely your own, and that AI-generated text is not copyrightable, not considered original authorship, and may violate publishing contract warranties. The document warns that all major commercial LLMs were trained on pirated, unlicensed books without compensating authors, and that AI outputs may contain fabricated information, biases, or regurgitated copyrighted material from training data.

The recommended practices span a spectrum of AI uses, from acceptable background research and spell-checking to ethically problematic direct copying of AI-generated text into professionally authored work. Key recommendations include disclosing AI-generated content on copyright registration applications, informing publishers and agents of any AI use, fact-checking all AI outputs, and publicly disclosing substantial AI text generation to readers. Authors are also urged to protect fellow creators — including translators, illustrators, narrators, and voice actors — by avoiding AI tools that displace human professionals and by seeking out models trained on licensed content. The Guild additionally advises writers to use written contracts with ghostwriters and collaborators that prohibit undisclosed AI-generated text, and to be cautious about uploading drafts or research into public chatbots that may use inputs for model training.