Will AI Replace Interface Designers? Sure, Why Not?
July 20, 2023
![Vea4_thumb_thumb_thumb_thumb_thumb_t[1]](http://arnoldit.com/wordpress/wp-content/uploads/2023/07/Vea4_thumb_thumb_thumb_thumb_thumb_t1-35.gif "Vea4_thumb_thumb_thumb_thumb_thumb_t[1]")
Note: This essay is the work of a real and still-alive dinobaby. No smart software involved, just a dumb humanoid.
Lost in the flaming fluff surrounding generative AI is one key point: Successful queries require specialized expertise. A very good article from the Substack blog Public Experiments clearly explains why “Natural Language Is an Unnatural Interface.”
A modern, intuitive, easy-to-use interfaces. That’s the ticket, MidJourney. Thanks for the output.
We have been told to approach ChatGPT and similar algorithms as we would another human. That’s persuasive marketing but terrible advice. See the post for several reasons this is so (beyond the basic fact that AIs are not humans.) Instead, advises writer Varun Shenoy, developers must create user-friendly interfaces that carry one right past the pitfalls. He explains:
“An effective interface for AI systems should provide guardrails to make them easier for humans to interact with. A good interface for these systems should not rely primarily on natural language, since natural language is an interface optimized for human-to-human communication, with all its ambiguity and infinite degrees of freedom. When we speak to other people, there is a shared context that we communicate under. We’re not just exchanging words, but a larger information stream that also includes intonation while speaking, hand gestures, memories of each other, and more. LLMs unfortunately cannot understand most of this context and therefore, can only do as much as is described by the prompt. Under that light, prompting is a lot like programming. You have to describe exactly what you want and provide as much information as possible. Unlike interacting with humans, LLMs lack the social or professional context required to successfully complete a task. Even if you lay out all the details about your task in a comprehensive prompt, the LLM can still fail at producing the result that you want, and you have no way to find out why. Therefore, in most cases, a ‘prompt box’ should never be shoved in a user’s face. So how should apps integrate LLMs? Short answer: buttons.”
Users do love buttons. And though this advice might seem like an oversimplification, Shenoy observes most natural-language queries fall into one of four categories: summarization, simple explanations, multiple perspectives, and contextual responses. The remaining use cases are so few he is comfortable letting ChatGPT handle them. Shenoy points to GitHub Copilot as an example of an effective constrained interface. He feels so strongly about the need to corral queries he expects such interfaces will be *the* products of the natural language field. One wonders—when will such a tool pop up in the MS Office Suite? And when it does, will the fledgling Prompt Engineering field become obsolete before it ever leaves the nest?
Cynthia Murrell, July 20, 2023
Comments
-
- Subscribe to Beyond Search
Feature archive
News archive
-
