Prompt engineers not only need to get the model to respond to a given question but also structure the output in a parsable way (such as JSON), in case it needs to be rendered in some UI components or be chained into the input of a future LLM query. They scaffold the raw input that is fed into an LLM so the end user doesn’t need to spend time thinking about prompting at all.

From the user’s side, it’s hard to decide what to ask while providing the right amount of context.From the developer’s side, two problems arise. It’s hard to monitor natural language queries and understand how users are interacting with your product. It’s also hard to guarantee that an LLM can successfully complete an arbitrary query. This is especially true for agentic workflows, which are incredibly brittle in practice.

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

most people use LLMs for ~4 basic natural language tasks, rarely taking advantage of the conversational back-and-forth built into chat systems:Summarization: Summarizing a large amount of information or text into a concise yet comprehensive summary. This is useful for quickly digesting information from long articles, documents or conversations. An AI system needs to understand the key ideas, concepts and themes to produce a good summary.ELI5 (Explain Like I'm 5): Explaining a complex concept in a simple, easy-to-understand manner without any jargon. The goal is to make an explanation clear and simple enough for a broad, non-expert audience.Perspectives: Providing multiple perspectives or opinions on a topic. This could include personal perspectives from various stakeholders, experts with different viewpoints, or just a range of ways a topic can be interpreted based on different experiences and backgrounds. In other words, “what would ___ do?”Contextual Responses: Responding to a user or situation in an appropriate, contextualized manner (via email, message, etc.). Contextual responses should feel organic and on-topic, as if provided by another person participating in the same conversation.

Prompting nearly always gets in the way because it requires the user to think. End users ultimately do not wish to confront an empty text box in accomplishing their goals. Buttons and other interactive design elements make life easier.The interface makes all the difference in crafting an AI system that augments and amplifies human capabilities rather than adding additional cognitive load.Similar to standup comedy, delightful LLM-powered experiences require a subversion of expectation.

Users will expect the usual drudge of drafting an email or searching for a nearby restaurant, but instead will be surprised by the amount of work that has already been done for them from the moment that their intent is made clear. For example, it would a great experience to discover pre-written email drafts or carefully crafted restaurant and meal recommendations that match your personal taste.If you still need to use a text input box, at a minimum, also provide some buttons to auto-fill the prompt box. The buttons can pass LLM-generated questions to the prompt box.

Whenever Facebook changes its interface, it has an impact on how millions of people communicate. In this sense, user interfaces are cultural artefacts.

If I had to guess why "math reform" is misinterpreted as "math education reform", I would speculate that school is the only contact that most people have had with math. Like school-physics or school-chemistry, math is seen as a subject that is taught, not a tool that is used. People don't actually use math-beyond-arithmetic in their lives, just like they don't use the inverse-square law or the periodic table.

Teach the current mathematical notation and methods any way you want -- they will still be unusable. They are unusable in the same way that any bad user interface is unusable -- they don't show users what they need to see, they don't match how users want to think, they don't show users what actions they can take.

They are unusable in the same way that the UNIX command line is unusable for the vast majority of people. There have been many proposals for how the general public can make more powerful use of computers, but nobody is suggesting we should teach everyone to use the command line. The good proposals are the opposite of that -- design better interfaces, more accessible applications, higher-level abstractions. Represent things visually and tangibly. And so it should be with math. Mathematics, as currently practiced, is a command line. We need a better interface.

Anything that remains abstract (in the sense of not concrete) is hard to think about... I think that mathematicians are those who succeed in figuring out how to think concretely about things that are abstract, so that they aren't abstract anymore. And I believe that mathematical thinking encompasses the skill of learning to think of an abstract thing concretely, often using multiple representations – this is part of how to think about more things as "things". So rather than avoiding abstraction, I think it's important to absorb it, and concretize the abstract... One way to concretize something abstract might be to show an instance of it alongside something that is already concrete.

The mathematical modeling tools we employ at once extend and limit our ability to conceive the world. Limitations of mathematics are evident in the fact that the analytic geometry that provides the foundation for classical mechanics is insufficient for General Relativity. This should alert one to the possibility of other conceptual limits in the mathematics used by physicists.

You can look at an interface and see it as a clearly signposted user journey you should follow. Or you can see it as a collection of functions and affordances to repurpose. As raw material, rather than a guided path.

The industrial designers talked about contours that felt gratifying in the hand and actions that provided a fidget-like comfort such as flipping the lid of a Zippo lighter or the satisfying click of a pen.

In video games, the button you press to make a character jump is often a simple binary input (pressed or not), and yet the output combines a very finely-tuned choreography of interactions, animations, sounds, particles, and camera shake to create a rich composition of sensations. The same jump button can feel like a dainty hop or a powerful leap. “Game feel” (a.k.a. “juice”) is the “aesthetic sensation of control” (Steve Swink, Game Feel) you have when playing a game.

The difference comes down to choice—which is to say, Design (with a capital “D”). Game feel is what makes some games feel gratifying to play (a character gliding down a sand dune) and others feel frustrating (sticky jumping, sliding). These decisions become a signature part of a game’s aesthetic feel and gameplay.

The Browser Company has written that software can optimize for emotional needs rather than just functional needs. Jason Yuan has promoted the idea of “fidgetability” where, similar to a key fob or lighter, digital actions can be designed to feel satisfying. Rahul Vohra has talked about making interfaces that are first fun as a toy—enjoyable to use without any greater aim.

The 2D portion is a particle simulation that “feeds” the growing sphere made with Lottie. It’s inspired by the charging animation common in games before your character delivers a big blow. Every action needs a windup. A big action—in order to feel big—needs a big wind up.

This is the big moment—it has to feel gratifying. We again combine 2D and 3D elements. The sphere and checkmark pop in and a massive starburst fills the screen like an enemy hit in Hollow Knight.

Our digital products are trapped behind a hard pane of glass. We use the term “touch”, but we never really touch them. To truly Feel a digital experience and have an app reach through that glass, requires the Designer to employ many redundant techniques. Video games figured this out decades ago. What the screen takes away, you have to add back in: animation, sound, and haptics.