The Long Case Against Chat

In January 2023, Austin Z. Henley wrote:

Expecting users to primarily interact with software in natural language is lazy.

Henley rightly argued that chat puts the onus on the user of figuring what to ask and how to ask it. Good interfaces guide people and help them discover what’s possible. He doubted that natural language should be the primary interface.

That same year, Amelia Wattenberger wrote:

Good tools make it clear how they should be used. And more importantly, how they should not be used. If we think about a good pair of gloves, it’s immediately obvious how we should use them. They’re hand-shaped! We put them on our hands. And the specific material tells us more: metal mesh gloves are for preventing physical harm, rubber gloves are for preventing chemical harm, and leather gloves are for looking cool on a motorcycle.

A blank text field doesn’t give the user a lot to go on. Wattenberger suggests that a chatbox with some additional affordances could help: dropdown menus for settings, or sliders for parameters to shape the response.

In January 2024, Elliot Smith predicted that chat would eventually occupy a narrower role:

Chat is unlikely to disappear but it’ll likely be for power users, much like the command line is today.

By 2025, Allen Pike was arguing that “chatting with the underlying LLM should be more of a debug interface—a fallback mode—and not the primary UX.” And at the time I agreed.

I’d already been arguing for a hybrid in my experiments with prompt-to-code tools. Starting with a prompt was useful, but once a design appeared, I wanted direct manipulation. At the time, apps like Lovable were very much prompting-only, unless you knew how to edit the code. As a designer, I wanted to click on some text and change its size.

I still agree with Wattenberger about the need for controls. But I’m having a harder time seeing plain language as a fallback or something mainly for power users. Pasting a grocery list into Amazon feels like a better way to shop. Just cut out the tedious middle part of searching, comparing, and adding to my cart. Just show me the outcomes. Increasingly, it’s the way I want to do all things on my computer.

Like Roger, I’ve also bet against chat being the primary interface for many while continuing to prefer to use it as the primary interaction. How has it been so durable? And how have these tools gotten ever more wider adoption?

My current hypothesis to answer, “(Why) is it different this time?”, is - LLMs are good at gleaning intent from our words. Independent of whether they are a verbal mashup - voice to text / short curt grammatically incorrect taps with the fingers - LLMs, especially within the context of other services - for example - Roger’s example of Alexa and Shopping - are really good at converting input into intent.

That’s different from the previous implementations of these - that needed specific trigger phrases and verbs and incantations to make the service work. Put another way - I am willing to be wrong in my own prediction in the past that chatbots / text isn’t going to be the interface for all.

Source: rogerwong.me