# AI and design

> AI and Design. There are two aspects: “Designing with the help of AI” and “Designing products/services with AI”.

[AI](https://wiki.g15e.com/en/pages/Artificial%20intelligence.txt) and [Design](https://wiki.g15e.com/en/pages/Design.txt). There are two aspects: "Designing with the help of AI" and "Designing products/services with AI".

## Designing with AI assistance

<ToDo>

Tools

- https://magicpath.ai
	- <Figma> style canvas
	- Generation at the component level
	- Design system management that looks pretty good
- https://beta.reweb.so
	- Figma style canvas
	- Generation at the component level
	- Theme management

## Product/service design with AI

Sometimes the most important outcome is the experience of creating something, rather than the artifact the tool produces. In this case, [Over-automation](https://wiki.g15e.com/en/pages/Over-automation.txt) may actually be a disadvantage. Note: [Values in the process](https://wiki.g15e.com/en/pages/Values%20in%20the%20process.txt)

---

Automation should be applied in a way that complements human shortcomings and enhances strengths. The algorithm that recommends news similar to the news I read reinforces a human weakness (<Selective exposure>).

---

Automation must provide not only reinforcing feedback (<Reinforcing feedback loop>) but also balancing feedback (<Balancing feedback loop>).

---

Good UI practices:

- https://aitestkitchen.withgoogle.com/tools/music-fx-dj

## Publications

Books:

- [Human-centered AI](https://wiki.g15e.com/pages/Human-centered%20AI%20(book.txt))
- [People + AI guidebook](https://wiki.g15e.com/pages/People%20+%20AI%20guidebook.txt) (by <Google>)
- <Weapons of math destruction>

Papers:

- [Beyond safety: Toward a value-sensitive approach to the design of AI systems](https://wiki.g15e.com/pages/Beyond%20safety%20-%20Toward%20a%20value-sensitive%20approach%20to%20the%20design%20of%20AI%20systems.txt)
- <Value Sensitive Design: Shaping technology with moral imagination>
- [Designing multispecies worlds for robots, cats, and humans](https://wiki.g15e.com/pages/Designing%20multispecies%20worlds%20for%20robots,%20cats,%20and%20humans.txt)
- [Automatic generation of visualizations and infographics with LLMs](https://wiki.g15e.com/pages/Automatic%20generation%20of%20visualizations%20and%20infographics%20with%20LLMs.txt)
- [Evaluating large language models in generating synthetic HCI research data](https://wiki.g15e.com/pages/Evaluating%20large%20language%20models%20in%20generating%20synthetic%20HCI%20research%20data.txt)

## Miscellaneous notes

- 2023-12 [Bottleneck of AI-Human interaction loop](https://wiki.g15e.com/en/pages/Bottleneck%20of%20AI-Human%20interaction%20loop.txt)
- 2023-12-12 - [Designing for AI: Panel Notes](https://www.lukew.com/ff/entry.asp?2043) by LukeW
    - Chat is a very flexible interface, people can define how they want to use it and when they want to use it. But it is a very direct interaction with the model itself. There's few affordances to help people understand the capabilities and limitations they are interacting with.
    - Text is a very imprecise medium, it's good for general direction but more controls are needed for specific use cases. In the future, we'll have a lot more powerful interfaces to AI models.
- 2023-12 - Google Gemini demo. [How to create UI on the fly](https://www.youtube.com/watch?v=v5tRc_5-8G4&t=2s)
- 2023-03 - [Building humane UI with LMs](https://www.youtube.com/watch?v=kqFNjIBdXAc)
    - The argument is that although the current method is centered on "Text-in / Text-out", in fact, the "Anything-you-can-turn-into-text in / Anything-you-can-create-from-text out" method is possible.
    - I think "Natural language-in / natural language-out" describes the current approach more accurately than "Text-in / Text-out." "Text-in / Text-out" is the traditional Unix CLI. The advantage of the "NL-in / NL-out" approach enabled by LLMs is more flexible composition (compared with the traditional <UNIX> CLI). "Anything-you-can-turn-into-text in / Anything-you-can-create-from-text out" could inadvertently undermine that flexibility. In the Google Gemini demo, [the approach that creates UI on the fly](https://www.youtube.com/watch?v=v5tRc_5-8G4&t=2s) lets you interact with the resulting UI, but feels harder to compose than "NL-in / NL-out."

## Articles

- 2025-04-15 - [User research, AI, and insight from practitioners: Eunhee Kim](https://maily.so/tipster/posts/8do78dnyrgq)
- 2024-05-13 - [A Design Space for Intelligent and Interactive Writing Assistants](https://programs.sigchi.org/chi/2024/program/content/146994)
- 2024-05-11- [DirectGPT: A Direct Manipulation Interface to Interact with Large Language Models](https://dl.acm.org/doi/10.1145/3613904.3642462)
- 2024-02-16 - [The UX of AI: Lessons from Perplexity](https://www.nngroup.com/articles/perplexity-henry-modisett/)
- 2024-02-16 - [AI Models and Headsets](https://www.lukew.com/ff/entry.asp?2052)
- 2023-10-27 - https://www.nngroup.com/articles/ai-roles-ux/
- 2023-03-03 - [How AI Technology Will Transform Design](https://www.smashingmagazine.com/2023/03/ai-technology-transform-design/)

## Tools

- https://readdy.ai - Similar to v0.dev, but explicitly positioned as a "service for designers."
	- Select shadcn/ui, etc. from the drop-down and enter the prompt to generate code.
	- When you click a specific link on the created screen, the page corresponding to "that link" is created. Example: Clicking the "Blog Post Title" link on the "Blog List" screen creates the "Blog Body" screen, and so on.
- https://magicpath.ai