Further Reading — Chapter 14: Using AI Effectively

Prompt Engineering and AI Interaction

Wei, J., et al. "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models." Advances in Neural Information Processing Systems (NeurIPS), 2022. The foundational research paper documenting how asking models to "think step by step" improves performance on reasoning tasks. The results are striking and directly applicable to everyday AI use. Tier: Primary — establishes the evidence base for a core technique in this chapter.

Brown, T. B., et al. "Language Models Are Few-Shot Learners." Advances in Neural Information Processing Systems (NeurIPS), 2020. The GPT-3 paper that demonstrated the power of few-shot prompting — showing that large language models can perform new tasks when given just a few examples in the prompt. Technical in places, but the introduction and results sections are accessible to non-specialists. Tier: Primary — essential context for understanding why few-shot prompting works.

Zamfirescu-Pereira, J. D., et al. "Why Johnny Can't Prompt: How Non-AI-Experts Try (and Fail) to Design LLM Prompts." CHI 2023: ACM Conference on Human Factors in Computing Systems, 2023. A research study examining how non-expert users interact with language models and the common mistakes they make. Directly relevant to building practical prompting skills. Tier: Recommended — connects research to the practical challenges discussed in this chapter.

AI Evaluation and Verification

Ji, Z., et al. "Survey of Hallucination in Natural Language Generation." ACM Computing Surveys, 2023. A comprehensive survey of the hallucination problem in language models — what causes it, how prevalent it is, and what techniques exist (and do not exist) to mitigate it. Useful for understanding why verification is essential. Tier: Recommended — deepens understanding of the verification challenge.

Rawte, V., Sheth, A., and Das, A. "A Survey of Hallucination in Large Foundation Models." arXiv preprint, 2023. An accessible overview of hallucination across different types of foundation models, not just text. Includes useful categorizations of hallucination types and their causes. Tier: Supplementary — for readers who want a broader perspective on hallucination beyond text.

Academic Integrity and AI

Perkins, M. "Academic Integrity Considerations of AI Large Language Models in the Post-Pandemic Era: ChatGPT and Alternative AI Tools." Journal of University Teaching and Learning Practice, 2023. An early and thoughtful analysis of how generative AI tools challenge traditional academic integrity frameworks. Discusses both the risks and the opportunities, with practical recommendations for educators and students. Tier: Recommended — directly relevant to Section 14.4.

Cotton, D. R. E., Cotton, P. A., and Shipway, J. R. "Chatting and Cheating: Ensuring Academic Integrity in the Era of ChatGPT." Innovations in Education and Teaching International, 2024. Examines the tension between AI as a learning tool and AI as a cheating tool, with case studies from multiple disciplines. Balanced and practical. Tier: Supplementary — useful for readers interested in the institutional perspective.

Professional AI Use

Metz, C. "What Google Learned from Its Quest to Build the Perfect Team." The New York Times Magazine, 2024. While not exclusively about AI, this piece explores how organizations are rethinking collaboration in light of AI tools — including the tension between efficiency and the kinds of learning that only happen through human struggle. Tier: Supplementary — broader context for professional AI use.

Varanasi, L. and Mahmud, H. "How Human-AI Collaboration Changes the Way People Evaluate AI." Proceedings of the ACM on Human-Computer Interaction, 2023. Research on how working alongside AI changes our ability to evaluate AI output — including the finding that collaboration can sometimes decrease critical evaluation. Directly relevant to the chapter's emphasis on maintaining critical judgment. Tier: Recommended — important empirical evidence for the verification argument.

Books for Deeper Exploration

Mollick, E. Co-Intelligence: Living and Working with AI. Portfolio/Penguin, 2024. A practical, research-grounded guide to using AI tools effectively, written by a Wharton professor who has extensively studied AI in education and work contexts. Highly readable and directly relevant to this chapter. Tier: Primary — the single best book-length resource on this chapter's topics.

Crawford, K. Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence. Yale University Press, 2021. While broader in scope than this chapter, Crawford's analysis of the power dynamics embedded in AI systems provides essential context for understanding why "responsible AI use" is not just a personal choice but a political one. Tier: Recommended — deepens the structural analysis.

Online Resources

OpenAI. "Prompt Engineering Guide." OpenAI Documentation, updated regularly. A practical, evolving guide to prompting techniques from one of the major model providers. Useful for hands-on practice, though remember that techniques may vary across different models. Tier: Supplementary — practical reference for ongoing skill development.

Google. "Prompt Design Strategies." Google AI Documentation, updated regularly. Google's equivalent resource, with examples specific to their models. Comparing the recommendations from different providers can itself be a useful learning exercise. Tier: Supplementary — comparative reference.