The most powerful thing a product can do is give its user a premise.1 A premise is the foundational belief that shapes a user’s behavior. A premise can normalize actions that people otherwise might not take, held back by some existing norm

AirBnb. The premise: It’s ok to stay in strangers’ homes.

the idea of staying in strangers’ homes for short stays was doubted even by the founders. Crashing in someone’s spare room wasn’t unheard of, but it might be seen as weird, taboo, or even dangerous.

Bumble. The premise: It’s ok for women to ask men out.

The best way to follow through on a premise is to make it the core feature of the app. Bumble did, requiring that women make the first move on the app. A woman would be presented with a list of her matches and would have to make the first "move" before men could reply. This of course became a powerful differentiating feature and marketing hook.

Substack. The premise: It’s ok to charge for your writing.

Substack's premise aimed to normalize the hardest part of internet writing: getting paid. They aimed to show that independent authors could succeed at making a living (and subscription models aligned with this ethos). In doing so, Substack also made the less-hard parts of internet writing even easier. You could start a newsletter and keep it free until you felt confident about going paid. This not only normalized the end goal but also lowered the barrier to getting started.

A premise is valuable not only for “products,” but also for experiences.As I recently shouted, people still underestimate the power of giving a social event a premise. Hackathons, housewarmings, happy hours and the like are hangouts with a narrative. They have a good premise — a specific context that makes it more comfortable to do something that can be hard: socialize. (Side note: some of the best tv series and films are built on great premises.)

Premises work best on end consumers, prosumers, small business freelancers, and the like. Many two-sided marketplaces serving two of these stakeholder groups tend to have a good premise. For example, Kickstarter's premise for the creator might be: It’s ok to ask for money before you've built a product.

in 2023, I switched gears to emphasize intimacy. Instead of statistical analysis and summative interviews, I sat next to individuals for hours, as they used one-off prototypes which I’d made just for them. And I got more insight in the first few weeks of this than I had in all of 2022

I’d been building systems and running big experiments, and I could tell you plenty about forgetting curves and usage patterns—but very little about how those things connected to anything anyone cared about.

I could see, in great detail, the texture of the interaction between my designs and the broader learning context—my real purpose, not some proxy.

Single-user experiments like this emphasize problem-finding and discovery, not precise evaluation.

a good heuristic for evaluating my work seems to be: try designs 1-on-1 until they seem to be working well, and only then run more quantitative experiments to understand how well the effect generalizes.

My aim is to invent augmented reading environments that apply to any kind of informational text—spanning subjects, formats, and audiences. The temptation, then, is to consider every design element in the most systematic, general form. But this again confuses aims with methods. So many of my best insights have come from hoarding and fermenting vivid observations about the particular—a specific design, in a specific situation. That one student’s frustration with that one specific exercise.

It’s often hard to find “misfits” when I’m thinking about general forms. My connection to the problem becomes too diffuse. The object of my attention becomes the system itself, rather than its interactions with a specific context of use. This leads to a common failure mode among system designers: getting lost in towers of purity and abstraction, more and more disconnected from the system’s ostensible purpose in the world.

I experience an enormous difference between “trying to design an augmented reading environment” and “trying to design an augmented version of this specific linear algebra book”. When I think about the former, I mostly focus on primitives, abstractions, and processes. When I think about the latter, I focus on the needs of specific ideas, on specific pages. And then, once it’s in use, I think about specific problems, that specific students had, in specific places. These are the “misfits” I need to remove as a designer.

Of course, I do want my designs to generalize. That’s not just a practical consideration. It’s also spiritual: when I design a system well, it feels like I’ve limned hidden seams of reality; I’ve touched a kind of personal God. On most days, I actually care about this more than my designs’ utilitarian impact. The systems I want to build really do require abstraction and generalization. Transformative systems really do often depend on powerful new primitives. But more and more, my experience has been that the best creative fuel for these systematic solutions often comes from a process which focuses on particulars, at least for long periods at a time.

Also? The particular is often a lot more emotionally engaging, day-to-day. That makes the work easier and more fun.

Throughout my career, I’ve struggled with a paradox in the feeling of my work. When I’ve found my work quite gratifying in the moment, day-to-day, I’ve found it hollow and unsatisfying retrospectively, over the long term. For example, when I was working at Apple, there was so much energy; I was surrounded by brilliant people; I felt very competent, it was clear what to do next; it was easy to see my progress each day. That all felt great. But then, looking back on my work at the end of each year, I felt deeply dissatisfied: I wasn’t making a personal creative contribution. If someone else had done the projects I’d done, the results would have been different, but not in a way that mattered. The work wasn’t reflective of ideas or values that mattered to me. I felt numbed, creatively and intellectually.

Progress often doesn’t look like progressIt often feels like I’m not making any progress at all in my work. I’ll feel awfully frustrated. And then, suddenly, a tremendous insight will drive months of work. This last happened in the fall. Looking back at those journals now, I’m amused to read page after page of me getting so close to that central insight in the weeks leading up to it. I approach it again and again from different directions, getting nearer and nearer, but still one leap away—so it looks to me, at the time, like I’ve got nothing. Then, finally, when I had the idea, it felt like a bolt from the blue.

This paper maps concepts from AI alignment onto a basic, three step interaction cycle, yielding a corresponding set of alignment objectives: 1) specification alignment: ensuring the user can efficiently and reliably communicate objectives to the AI, 2) process alignment: providing the ability to verify and optionally control the AI's execution process, and 3) evaluation support: ensuring the user can verify and understand the AI's output.

the notion of a Process Gulf, which highlights how differences between human and AI processes can lead to challenges in AI control.

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.

However the most controversial step I’ll be taking is removing a few of the functions. This usually gets pushback from most product managers as for them “features == sales”. The problem with this thinking is that it assumes a) all features are used and b) extra features has no negative impact.

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.

be inspired by the untapped potential of human capabilities. Don't just extrapolate yesterday's technology and then cram people into it.

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.

Let’s say you present 3 directions to a client: directions A, B, and C. These are our initial 3 branches. You have a client review, direction C is the winner, and so you iterate again. 3 more branches: C1, C2, and C3. Another review, another winner, another round of iterations: C2.1, C2.2, C2.3. Branch out, choose one, zoom in, branch out, repeat.

Sometimes, the design process requires us to zoom out. Let’s say you present those 3 creative directions, A, B, and C, but nothing lands. Back to the drawing board. You might keep pushing forward with branches D, E, F. Nothing lands. You’re forced to zoom out and realize that you’re not even on the right parent branch.

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.

In other words, when Kylie Jenner posts a petition demanding that Meta “Make Instagram Instagram again”, the honest answer is that changing Instagram is the most Instagram-like behavior possible.

The first trend is the shift towards ever more immersive mediums. Facebook, for example, started with text but exploded with the addition of photos. Instagram started with photos and expanded into video. Gaming was the first to make this progression, and is well into the 3D era. The next step is full immersion — virtual reality — and while the format has yet to penetrate the mainstream this progression in mediums is perhaps the most obvious reason to be bullish about the possibility.

The second trend is the increase in artificial intelligence. I’m using the term colloquially to refer to the overall trend of computers getting smarter and more useful, even if those smarts are a function of simple algorithms, machine learning, or, perhaps someday, something approaching general intelligence.

The third trend is the change in interaction models from user-directed to computer-controlled. The first version of Facebook relied on users clicking on links to visit different profiles; the News Feed changed the interaction model to scrolling. Stories reduced that to tapping, and Reels/TikTok is about swiping. YouTube has gone further than anyone here: Autoplay simply plays the next video without any interaction required at all.