Making Exercise Nine: Generation

AI-assisted code generation offers great potential for meaningful critical making projects—especially when approached as a conversation between human intent and machine output. The work of generation is collaborative and iterative: you guide the process through prompting, evaluating, and refining, while the AI assists with code, structure, and design. Quirks and emergence can contribute to the overall work, and we embrace these much like Marshall McLuhan’s famous cover typo of “massage” instead of “message.” As you engage in generation, consider:

• Probe the conversational limitations. Try starting vague, or working with different ways of phrasing and expressing ideas to see where meaning is conveyed and where it is lost. These conversations are in part an opportunity to see what is included in the underlying archives (training data)—can you tell what might be missing?
• Explore a range of expressive outputs. Machine learning models are particularly powerful for assistance in programming and development work, as tools like GitHub Copilot suggest: in time, it’s likely these tools will be an inescapable part of certain workflows. Think about where the AI assists your making, and where it is limiting.
• Contextualize the experience. How does the system you are co-creating with reflect the headlines, fears, and assumptions that both generations of science fiction writers and current journalists have centered in their visions of AI futures?

Getting Started

If you’re looking for inspiration, here are three project types you can use as a starting point. Each is modeled on the workshop exercises at Distant Coding with Claude Code, where you can see sample outputs and detailed walkthroughs. You are not limited to these—feel free to adapt them or pursue a different generative project entirely.

Option A: Building an ePortfolio from a CV

Upload your CV (as a Word document or PDF) to a GitHub repository and use Claude Code to transform it into a single-page portfolio website. Through conversation, guide the AI to analyze your document, design an appropriate aesthetic, and build a site with sections for your publications, presentations, teaching, projects, awards, and education. Deploy the result via GitHub Pages.

Option B: Distant Reading a Text Corpus

Select three to five plain-text files from Project Gutenberg related to a theme or research interest. Use Claude Code to preprocess the texts (stripping formatting, tokenizing, removing stopwords, computing word frequencies), identify shared key terms, and extract keyword-in-context concordances. Then have Claude build an interactive web visualization displaying word distributions, frequency comparisons, and searchable concordance data, deployed via GitHub Pages.

Option C: Image Metadata and Slideshow from Photographs

Gather a set of your own photographs (or public domain images) around a theme. Use Claude Code to analyze each image, generate descriptive alt-text for accessibility, and rename files meaningfully. Then guide Claude to construct a themed slideshow using reveal.js with custom styling and captions, deployed via GitHub Pages.

How to Work

For AI-assisted coding in this course, I recommend using Claude Code in your browser, which provides an integrated environment for conversational code generation and debugging without requiring local installation. Claude Code can access and modify a GitHub repository, generate your project files, and deploy directly to GitHub Pages—all through conversation.

If you do not have a Claude subscription, you can still complete any of these projects by working indirectly: use a free AI assistant (such as claude.ai free tier or another tool) to generate HTML, CSS, and JavaScript files through conversation, then manually upload them to a GitHub repository and enable GitHub Pages yourself.

Reflection

Whichever project you choose, document your process and reflect critically on the experience. Keep in mind the readings in both Design Justice and Your Computer is On Fire, and make specific connections to the problems raised by these tools using those lenses. In your reflection, address:

• Which aspects of your project benefited from AI assistance? Which were impeded by it?
• What did the conversation reveal about the AI’s assumptions, gaps, or biases?
• How does the experience of co-creating with an AI connect to broader questions about labor, authorship, and justice in digital making?