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.

Anthropic's guide to prompt engineering best practices for 2026 walks through a progression of techniques for getting better results from AI models like Claude. The article starts with core techniques — being explicit and clear, providing context and motivation, adding specificity, using examples (few-shot prompting), and giving the model permission to express uncertainty. These foundational habits are positioned as the starting point before moving to more sophisticated methods.

The guide then covers advanced techniques including response prefilling to enforce output formats like JSON, chain of thought prompting (with basic, guided, and structured variants), output format control, and prompt chaining — breaking complex tasks into sequential steps across multiple prompts. Notably, the article acknowledges that some once-popular techniques like XML tags and heavy role prompting are now less necessary with modern models like Claude 4.x, which can interpret structure and intent more naturally.

A practical decision framework helps readers choose the right technique for their situation, while a troubleshooting section addresses common problems like generic responses, hallucinations, and inconsistent formatting. The article emphasizes that prompt engineering is converging with context engineering for newer Claude models, where the focus shifts from scaffolding prompts to curating the right context. The overarching advice: start simple, add complexity only when needed, and remember that the best prompt is the one that achieves goals reliably with minimum structure.

This guide from Prompt Engineering Guide outlines foundational tips for designing effective prompts for large language models. It emphasizes starting simple and iterating incrementally, treating prompt design as an experimental process where complexity is added gradually. The guide recommends using clear command verbs like "Write," "Classify," or "Summarize" and separating instructions from context with delimiters like "###" for clarity.

A central theme is the importance of specificity over vagueness — rather than asking for "a short explanation," a well-crafted prompt specifies the exact length, audience, and format desired. The guide also addresses the common pitfall of telling models what not to do, demonstrating through a movie recommendation chatbot example that positive instructions (stating what the model should do) produce far better results than negative constraints. Each tip is illustrated with concrete before-and-after prompt examples, making the advice immediately actionable for practitioners at any level.