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.

as I’ve wrestled with writing this, it’s clear that many just don’t see the problem, as they assume a cheap button is nearly as good as a proper dial. They’ll openly admit a dial is indeed better but a cheap button is “good enough” and that a dial is “just too expensive.” That actually may be true! There are cases when using a push button is the right choice. But not always. We need to understand when to try a bit harder. Yes, you’re spending a tiny bit more on hardware, but you’re creating a product that is usually much easier to use, reduces returns, and builds your brand which improves sales. Is this positive outcome a given? Of course not, nothing is guaranteed but we need to stop pretending there is NO COST to cheaping out on buttons.

The dial changes the frequency with a simple twist. The push button device “Deconstructs” the twist dial into two up/down buttons. Each press increments the frequency a tiny amount. This means a twist is replaced with many button presses. Again, they are ‘functionally equivalent’ but the expression and ease of use are quite different.

“Adding a feature” is never free. Always start with the user’s problems first. If pressed into using one of these four abuses, make sure to fully appreciate its impact, the friction it creates, and what you can do to work around it.  Adding a feature shouldn’t also “add a problem.”

As a professional UX Designer, I want devices to offer more. But UX Design isn’t about cramming everything into your product in the vague Hail Mary hope it’ll ship a few more units. That’s the sales team speaking, not the user. It’s the wrong motivation and creates monsters.

When content is shorter and maximized for engagement, we often lose track of the origin, history, and context behind it: a new designer is more likely to hear about a UX law from a UX influencer on an Instagram carousel than through the actual research which brought it about.The lack of nuance from algorithm-suggested posts undermines any value we could get from them. For a discipline known for asking "why" and for striving to understand users’ context, it’s time we become more intentional about our own information sources.

Shifts in visual narratives happen every decade or so, so it’s not surprising that the design world is moving away from the corporate flatness of web2. Instead of reminding us of the problems of our current world and the harm that’s been caused by Big Tech, the new, abstract forms of web3 distract us from the crises of the day with the promise of a new virtual world.

TikTok looked at what makes their content unique. Applying an OOUX mindset, the most interesting object is the “post” populating the feed. Two things stand out. First, the videos are very short, with only a couple of seconds of runtime. Which meant the usual distinction between browsing and watching made little sense. Second, opting for a truly mobile experience, their videos would be portrait mode. This meant users could browse and watch in the same orientation, one video at a time. The design decision to merge the browse and watch experience into one stream with autoplay broke all kinds of conventions. Yet, by doing so, it created a unique and engaging experience that is even borderline addictive.

Tinder understood that the selection moment is what makes them unique. They wanted to provide a quick and easy method for their key interaction to decide if a user is a match or not.

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.