Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish
Fish

Fish eyes

We often think of the same information at different levels or abstraction. Here's a simple example:

Here's a close-up of a fish— we can see the scales, the texture of the fins, the faint reflection in the eye.

An illustration of a fish, close up

Zoomed out a bit, the details are faded slightly. The surrounding ocean comes into view.

An illustration of a fish, medium zoom

Zooming out more, the fish is just a few splashes of color amongst a school of fish.

An illustration of a fish, far away in a school of fish

Maps work in a similar way.

Looking at a section of the National Zoo, we can see paths, buildings, and even animal enclosures!

A zoomed in Google map of the Reptile Discovery Center at the National Zoo

Zoomed out a little, and now it’s about neighborhoods—parks, stores, and streets.

A few zooms out on a Google map, looking at a few neighborhoods in DC

Keep zooming out and you’re looking at a city, with just the highways and terrain.

A further zoomed out Google map of the greater DC area

Each level gives you completely different information, depending on what Google thinks the user might be interested in. Maps are a true masterclass for visualizing the same information in a variety of ways.

So far, these are familiar examples. What if we applied the same principles to text?

Let's take a look at the opening paragraph of The Metamorphosis.

As Gregor Samsa awoke one morning from uneasy dreams he found himself transformed in his bed into a gigantic insect. He was laying on his hard, as it were armor-plated, back and when he lifted his head a little he could see his domelike brown belly divided into stiff arched segments on top of which the bed quilt could hardly keep in position and was about to slide off completely. His numerous legs, which were pitifully thin compared to the rest of his bulk, waved helplessly before his eyes.

Abstracted a little, we can remove some of the detail.

Gregor Samsa wakes from troubled sleep to find he's become a giant insect. He lies trapped on his hard shell-like back, observing his new segmented belly and thin legs moving helplessly.

And fully zoomed out, we can summarize the paragraph in a single sentence.

A man unexpectedly transforms into an insect while sleeping.

See how we can view even text at different levels of abstraction? For the interested, there's a little more detail in my AI Engineer Summit talk from 2023.

An illustration of a fish An illustration of a fish An illustration of a fish

Showing multiple levels at once

Viewing the same text at different levels of abstraction is powerful, but what, instead of switching between them, we could see multiple levels at the same time? How might that work?

Let's look at an analogy from photography. A portrait lens brings a single subject into focus, isolating it from the background to draw all attention to its details. A wide-angle lens captures more of the scene, showing how the subject relates to its surroundings. And then there’s the fish eye lens—a tool that does both, pulling the center close while curving the edges to reveal the full context.

A fish eye lens doesn’t ask us to choose between focus and context—it lets us experience both simultaneously. It’s good inspiration for how to offer detailed answers while revealing the surrounding connections and structures.

Often, we’re handed a single piece of text, stripped from its surroundings: a quote from a book, a paragraph from a Wikipedia article, or a sentence from a movie script. You're left filling in the context on your own, and often incorrectly.

Take this quote from The Game of Thrones:

Winter is coming.

Without the backdrop of the looming threat in Westeros, this is just a weather report. Within the series, it’s an ominous warning of existential danger. Viewing quotes out of context is like trying to understand a movie by watching one scene: inherently incomplete.

An illustration of a fish An illustration of a fish An illustration of a fish

Imagine you’re reading The Elves and the Shoemaker by The Brothers Grimm. You come across a single paragraph describing the shoemaker discovering the tiny, perfectly crafted shoes left by the elves. Without context, the paragraph is just an intriguing moment.

Now, what if instead of reading the whole book, you could hover over this paragraph and instantly access a layered view of the story? The immediate layer might summarize the events leading up to this moment: the shoemaker, struggling in poverty, left his last bit of leather out overnight. Another layer could give you a broader view of the story so far: the shoemaker’s business is mysteriously revitalized thanks to these tiny benefactors. Beyond that, an even higher-level summary might preview how the tale concludes, with the shoemaker and his wife crafting clothes for the elves to thank them.

The Elves and the Shoemaker

There was once a shoemaker, who worked very hard and was very honest: but still he could not earn enough to live upon; and at last all he had in the world was gone, save just leather enough to make one pair of shoes.
Then he cut his leather out, all ready to make up the next day, meaning to rise early in the morning to his work. His conscience was clear and his heart light amidst all his troubles; so he went peaceably to bed, left all his cares to Heaven, and soon fell asleep. In the morning after he had said his prayers, he sat himself down to his work; when, to his great wonder, there stood the shoes all ready made, upon the table. The good man knew not what to say or think at such an odd thing happening. He looked at the workmanship; there was not one false stitch in the whole job; all was so neat and true, that it was quite a masterpiece.
The same day a customer came in, and the shoes suited him so well that he willingly paid a price higher than usual for them; and the poor shoemaker, with the money, bought leather enough to make two pairs more. In the evening he cut out the work, and went to bed early, that he might get up and begin betimes next day; but he was saved all the trouble, for when he got up in the morning the work was done ready to his hand. Soon in came buyers, who paid him handsomely for his goods, so that he bought leather enough for four pair more. He cut out the work again overnight and found it done in the morning, as before; and so it went on for some time: what was got ready in the evening was always done by daybreak, and the good man soon became thriving and well off again.
One evening, about Christmas-time, as he and his wife were sitting over the fire chatting together, he said to her, ‘I should like to sit up and watch tonight, that we may see who it is that comes and does my work for me.’ The wife liked the thought; so they left a light burning, and hid themselves in a corner of the room, behind a curtain that was hung up there, and watched what would happen.
As soon as it was midnight, there came in two little naked dwarfs; and they sat themselves upon the shoemaker’s bench, took up all the work that was cut out, and began to ply with their little fingers, stitching and rapping and tapping away at such a rate, that the shoemaker was all wonder, and could not take his eyes off them. And on they went, till the job was quite done, and the shoes stood ready for use upon the table. This was long before daybreak; and then they bustled away as quick as lightning.
The next day the wife said to the shoemaker. ‘These little wights have made us rich, and we ought to be thankful to them, and do them a good turn if we can. I am quite sorry to see them run about as they do; and indeed it is not very decent, for they have nothing upon their backs to keep off the cold. I’ll tell you what, I will make each of them a shirt, and a coat and waistcoat, and a pair of pantaloons into the bargain; and do you make each of them a little pair of shoes.’
The thought pleased the good cobbler very much; and one evening, when all the things were ready, they laid them on the table, instead of the work that they used to cut out, and then went and hid themselves, to watch what the little elves would do.
About midnight in they came, dancing and skipping, hopped round the room, and then went to sit down to their work as usual; but when they saw the clothes lying for them, they laughed and chuckled, and seemed mightily delighted.
Then they dressed themselves in the twinkling of an eye, and danced and capered and sprang about, as merry as could be; till at last they danced out at the door, and away over the green.
The good couple saw them no more; but everything went well with them from that time forward, as long as they lived.
There was once a shoemaker, who worked very hard and was very honest: but still he could not earn enough to live upon; and at last all he had in the world was gone, save just leather enough to make one pair of shoes.
The impoverished yet diligent shoemaker had only leather for one final pair of shoes.
The industrious shoemaker received nightly aid from helpful elves who completed his unfinished work.

This approach allows you to orient yourself without having to piece everything together by reading linearly. You get the detail of the paragraph itself, but with the added richness of understanding how it fits into the larger story.

This specific example isn't the best, but alas there are only so many hours a day to play with code with a baby around. But I can imagine variations on it that would be more compelling. Even just a "grab a quote" interaction for articles that inserts some context around the quote would be really useful.

An illustration of a fish An illustration of a fish An illustration of a fish

Think about how we typically learn. Pick up a book, and context surrounds every piece of information. Chapters give structure, connecting each idea to the ones that came before and after. A good author sets the stage, immersing you with anecdotes, historical background, or thematic threads that help you make sense of the details. Even the act of flipping through a book—a glance at the cover, the table of contents, a few highlighted sections—anchors you in a broader narrative.

Think about learning something from a person. Let’s say a friend tells you about fancy goldfish. Their explanation doesn’t stop at naming the Oranda—they might tell you where they first saw one, why they think it’s fascinating, or how it’s a beloved species in Chinese culture, symbolizing luck and prosperity. The context of who is telling you the information—their expertise, interests, or personal connection—colors how you understand it.

Or take museums: when you see a fish displayed in an exhibit, the plaque beneath it doesn’t just name the species. It tells you where the fish lives, how it evolved, and maybe even its significance in art or mythology. The exhibit places the fish in an ecosystem of knowledge, helping you understand it in a way that goes beyond just a name.

Zooming Beyond the Answer

But when you ask an LLM chatbot, you don’t get any of that. It’s as if you opened a book to one random sentence, read it, and closed the book again. Sure, the answer might be accurate, even helpful—but it’s stripped of all the surrounding context that makes learning feel meaningful and complete.

Let's say you take a photo of a fish on vacation and want to know what it is.

What fish is this?

An illustration of a fish, close up

This appears to be a type of fancy goldfish, likely an Oranda or Fantail Goldfish, recognized for its flowing fins and vibrant coloration.

Not a bad answer, really! But we're fully zoomed in on just the answer to our question. Sure, you can ask follow-up questions—what does the Oranda eat, where does it live, how does it compare to other goldfish?—but the onus is entirely on you to know what to ask next. The chatbot is reactive, not proactive, and unless you’re already an ichthyology enthusiast, you might not know the right questions to even start exploring deeper.

Let's reimagine a Wikipedia a bit. In the center of the page, you see a detailed article about fancy goldfish—their habitat, types, and role in the food chain. Surrounding this are broader topics like ornamental fish, similar topics like Koi fish, more specific topics like the Oranda goldfish, and related people like the designer who popularized them.

Clicking on another topic shifts it to the center, expanding into full detail while its context adjusts around it. It’s dynamic, engaging, and most importantly, it keeps you connected to the web of knowledge.

Fancy Goldfish

Fancy goldfish are a domesticated variety of bred for unique physical characteristics and ornamental purposes. Unlike common goldfish, they have distinctive features such as bulging eyes, elaborate fins, and rounded body shapes. Originating in , these decorative fish are popular in home and ornamental . They come in various colors and types, including , , and goldfish. While beautiful, fancy goldfish generally have shorter lifespans and are less hardy than their wild counterparts due to selective breeding.

More specific topics
Similar topics
More general topics
Related people

You’re learning around a concept, immersing yourself in a connected web of ideas where one answer sparks curiosity about the next.

An illustration of a fish An illustration of a fish An illustration of a fish

What else could this apply to?

Where else could we apply a fish eye lens?

  • An illustration of a fish Timelines
    Key milestones are richly detailed and surrounding events fade into summaries, helping you see history as a dynamic continuum.
  • An illustration of a fish Code
    Picture a code editor where the function you’re working on is fully expanded, related functions are summarized nearby, and the overall structure of your codebase is abstracted above.
  • An illustration of a fish Education
    Textbooks or online courses could layer concepts so students can navigate effortlessly between detailed lessons and broader summaries.
  • An illustration of a fish Task management
    A to-do list could highlight today’s tasks in detail while showing summaries of weekly goals and overarching projects.

The beauty of a fish eye lens for text is how naturally it fits with the way we process the world. We’re wired to see the details of a single flower while still noticing the meadow it grows in, to focus on a conversation while staying aware of the room around us. Facts and ideas are never meaningful in isolation; they only gain depth and relevance when connected to the broader context.

This concept isn’t new—it’s foundational to fields like data visualization. A single number on its own might tell you something, but it’s the trends, comparisons, and relationships that truly reveal its story. Is 42 a high number? A low one? Without context, it’s impossible to say. Context is what turns raw data into understanding, and it’s what makes any fact—or paragraph, or answer—gain meaning.

The fish eye lens takes this same principle and applies it to how we explore knowledge. It’s not just about seeing the big picture or the fine print—it’s about navigating between them effortlessly. By mirroring the way we naturally process detail and context, it creates tools that help us think not only more clearly but also more humanly.

An illustration of coral.