Making is Decision Making

Human creation of high-quality content requires making decisions - from coarse, high-level decisions about content and style, to precise low-level decisions about the color of an individual pixel. Such creators often move between various levels of abstraction in this decision making typically starting with a rough initial draft and then iteratively refining it towards a final result. While modern generative AI tools are capable of producing surprisingly high-quality content from simple text prompts, they do not support such design exploration and iteration. Instead today’s AI tools are black boxes, making it impossible for users to build a mental/conceptual model that can predict how an input prompt will be transmuted into output content. The lack of predicatability forces users to rely on iterative trial-and-error, repeatedly crafting a prompt, using the AI to generate a result, and then adjusting the prompt to try again. In this talk I’ll outline some features generative AI tools should provide to support exploration and iterative refinement rather than iterative trial-and-error. These features include consistency of the output content from iteration to iteration. hierarchical decomposition of the creation task and support for rapid, reversible actions. Finally I’ll suggest some approaches we might use to build generative AI tools that provide such features and demonstrate a few implementations of these ideas that we have developed in our lab at Stanford.

Speaker: Maneesh Agrawala, Stanford University

Attend in person or online (see weblink)