The Problem with Chat — Remembering the Next Time

Open Menu<br>Close Menu

Remembering the Next Time

Open Menu<br>Close Menu

The Problem with Chat

Jun 30

Written By magfrump .

Large language models (LLMs) are a powerful new technology that is reshaping how we interact with computers. Despite the early and unexpected popularity of ChatGPT, Claude Code was the tool that started producing clear economic value. Among the reasons for this delay is that “chat” is a massive, 40+-year regression in interface design. The regression remains unfixed, and it creates an uncanny valley of interaction that underlies a lot of controversial discourse about AI.<br>Depending on who you are, any or all of these sentences may be surprising or controversial; potentially for more than one reason! You shouldn’t trust that they’re true just because you read the words I typed. So what would make these claims trustworthy?<br>I can describe to you why I believe them. For example, I believe that the popularity of ChatGPT was unexpected, because the original release was a tech demo, and OpenAI expressed publicly they had no expectation it would take off in chat-form. And I believe that chat is a 40 year interface regression because of a quote from a foundational 1985 paper on computer interfaces:<br>“Historically, most interfaces have been built on the conversation metaphor. There is power in the abstractions that language provides (we discuss some of this later), but the implicit role of interface as an intermediary to a hidden world denies the user direct engagement with the objects of interest.”

The reasoning and quote probably make my initial statement more convincing, unless you assume that I (the author) am an LLM, and everything I’ve typed could be completely made up. I could make it more convincing by adding citations: ChatGPT was a tech demo, it’s success was a surprise, the source for my quote (p.9 of the pdf). You can follow these links–it would be much more difficult for me to make up the web pages from scratch, hosted on the domain names for Business Insider and OpenAI, than to only make up the claims. You might then read the articles I’ve linked and come to the same conclusions, or you might come to different conclusions. In particular, the fact that pre-1985 interfaces were often “conversational” doesn’t mean that chat specifically is outdated as an interface! You might, for example, object that the chat interface has served you well in your own dealings with LLMs. In which case I would direct you to a different quote from Hutchins et. al 1985 (p.17 this time):<br>“Automatization is useful, for it improves the interaction of the user with the system, but the feeling of directness it produces depends only on how much practice a particular user has with the system and thus gives the system credit for the work the user has done.”

The overall paper discusses how we co-adapt with our computer interfaces, so that after experiencing chat interfaces for a few years, users will start to overlook their flaws because the user has adjusted their workflows around the interface.<br>This is going pretty deep on just one of the claims in my initial paragraph, and is purely analytical. Let’s try an empirical trial of this powerful new technology.<br>Chat transcript:<br>User input<br>is this true:<br>Large language models are a powerful new technology that is reshaping how we interact with computers. Despite the early and unexpected popularity of ChatGPT, Claude Code was the tool that started producing clear economic value. Among the reasons for this delay is that “chat" is a massive, 40+-year regression in interface design. The regression remains unfixed, and it creates an uncanny valley of interaction that underlies a lot of controversial discourse about AI.

Gemini 3.1 Pro (Standard thinking) responded:<br>This statement is a mix of undisputed fact, a significant historical inaccuracy, and a highly regarded critique from the world of User Experience (UX) and Human-Computer Interaction (HCI).<br>Here is a breakdown of the specific claims to separate what is true, what is false, and what is subjective but valid.<br>The False Premise: Claude Code and Economic Value<br>"Despite the early and unexpected popularity of ChatGPT, Claude Code was the tool that started producing clear economic value."<br>Verdict: False. While Claude Code (released by Anthropic in 2025) is a highly capable tool, claiming it was the first to produce "clear economic value" is historically inaccurate.<br>GitHub Copilot (launched in 2021, well before ChatGPT) is widely recognized as the first generative AI product to produce undeniable economic value by measurably increasing developer productivity.

ChatGPT itself drove massive economic value almost immediately upon release in late 2022, not just through OpenAI's subscription revenue, but by being integrated via API into thousands of enterprise workflows, customer service pipelines, and data analysis tools.

The Valid UX Critique: Chat as a...