Seeing with 30,000 eyes

Why our tools trap us in tunnel vision - and what dragonflies can teach us about breaking free

The psychologist Roy Baumeister has a name for what happens when we face too many decisions without sufficient processing capacity: "decision fatigue." But there's another, quieter form of cognitive depletion that's rarely discussed- what we might call perspective poverty.

You've felt it. That moment when you're four tabs deep into a research rabbit hole, switching between three half-finished projects, fielding Slack messages about a deadline that shifted yesterday, and suddenly you realize: you've lost the thread. Not just of the task at hand, but of why it matters. Your work has fractured into a thousand urgent fragments, each demanding attention, none connecting to anything larger.

The economist Herbert Simon saw this coming decades ago when he coined the term "attention economy." In a world rich with information, he argued, attention becomes the scarce resource. But Simon was describing scarcity. What we're experiencing now is something more insidious: fragmentation so complete that we've stopped noticing we're only seeing slivers of reality.

The Compound Eye Problem

Here's where things get interesting. In their remarkable book Superforecasting: The Art and Science of Prediction, Philip Tetlock and Dan Gardner describe what separates accurate forecasters from everyone else. It's not raw intelligence. It's not access to classified information. It's something they call "dragonfly vision."

The metaphor is visionary:

"Like us, dragonflies have two eyes, but theirs are constructed very differently. Each eye is an enormous, bulging sphere, the surface of which is covered with tiny lenses. Depending on the species, there may be as many as thirty thousand of these lenses on a single eye, each one occupying a physical space slightly different from those of the adjacent lenses, giving it a unique perspective. Information from these thousands of unique perspectives flows into the dragonfly's brain where it is synthesized into vision so superb that the dragonfly can see in almost every direction simultaneously, with the clarity and precision it needs to pick off flying insects at high speed."

Tetlock wasn't making idle comparisons. His decade-long forecasting tournament revealed that the best predictors - the "superforecasters" who consistently outperformed intelligence analysts with access to classified data - all shared this dragonfly trait. They actively sought out conflicting viewpoints. They triangulated between disciplines. They built their understanding not from a single authoritative source but from a synthesis of dozens of weak signals, each adding resolution to the larger picture.

The problem is neurological: human brains are magnificent at many things, but effortlessly integrating thirty thousand simultaneous perspectives isn't one of them. We're pattern-completion machines, built to find the narrative thread and follow it. Show us three data points and we'll draw a confident line through them, even when the fourth point - just out of view - would shatter our entire theory.

The Architecture of Synthesis

This is where most productivity advice fails. It tells you to close tabs, batch your email, time-block your calendar. All sensible… and all insufficient. Because the real challenge isn't managing your attention - it's managing your perspective.

Think about how you actually work on complex problems. You read an article that sparks an idea. Three days later, you're in a meeting where someone mentions something adjacent. A week after that, you stumble across a relevant dataset. The connections are there, but they're temporal ghosts, separated by enough time that your working memory can't hold them simultaneously. You know there's a pattern, but the pieces never quite assemble.

Neuroscientists call this the "binding problem" - how the brain integrates information processed in different regions at different times into a coherent whole. Your occipital lobe processes shapes while your temporal lobe handles identity, all at slightly different speeds. Yet somehow you see a unified image, not a fragmented mess.

Your brain solves this through what Francis Crick called the "neural correlates of consciousness" - synchronized firing patterns that temporarily bind disparate information. But this mechanism evolved for immediate sensory processing, not for synthesizing a insight from a paper you read last month, notes from a conversation you had yesterday, and data you just discovered.

We need external scaffolding. Not just storage - synthesis architecture.

Building Your Compound Eye

This is what Retain actually does, and why it represents something genuinely different.

Most knowledge tools are glorified filing cabinets. Clever ones, sure - searchable, taggable, cross-referenced - but fundamentally static. They help you find the note you took, assuming you remember you took it and can recall enough keywords to surface it. They're built on the assumption that your problem is retrieval.

But your problem isn't retrieval. It's integration.

Retain's Knowledge Graph works more like the dragonfly's visual cortex. Each note, document, or idea becomes a lens - a distinct perspective capturing a particular angle on reality. But the real intelligence emerges in how these lenses connect. The system doesn't just store your information; it maps the relationships between pieces, building what computer scientists call a semantic network.

This matters because of how human insight actually works. Cognitive psychologist Gary Klein spent years studying how experts make decisions under pressure - firefighters, nurses, pilots - and found that expertise isn't about having more knowledge. It's about having knowledge structured differently. Experts see patterns novices miss because their mental models encode relationships, not just facts.

The Knowledge Graph externalizes this structure. When you search or explore, you're not just retrieving matching documents - you're navigating the topology of your own thinking, seeing how ideas cluster, where unexpected connections emerge, which threads you've left dangling.

Ubiquitous, Not Scattered

But here's the catch: compound vision only works if all the lenses point in the same direction.

The dragonfly's thirty thousand lenses would be useless if half of them were stuck on yesterday's pond while the other half gazed at tomorrow's sky. Real-time integration is everything. This is why we need systems designed to gather meeting insights in real-time and synchronize across platforms. Your knowledge graph needs to be singular and current, accessible wherever cognition happens: at your desk, in transit, in that moment of unexpected clarity at 11 PM.

This architectural choice reflects a deeper understanding: knowledge work isn't confined to offices anymore. Insight doesn't wait for you to be at your desk. The synthesis you need might require connecting something from your morning commute reading with a detail from this afternoon's meeting. If those contexts live in different systems - or worse, in the same system that hasn't synced - the connection never forms.

The Practice of Multi-Perspective Thinking

None of this matters, of course, if it merely automates our existing habits. Technology that makes us better at being distracted isn't progress.

The real promise is this: by externalizing the architecture of synthesis, we can develop the practice of dragonfly vision. Multi-perspective is not just a one-off technique, but a fundamentally different way of working.

Tetlock's superforecasters didn't just collect multiple perspectives - they actively cultivated the habit of seeking disconfirming evidence, questioning their assumptions, updating their beliefs. The tools didn't think for them; the tools made a certain kind of thinking sustainable.

That's the shift. From managing information to building understanding. From reacting to synthesizing. From working harder to seeing clearer.

The dragonfly doesn't think about its thirty thousand lenses. It just flies, sees, and strikes with remarkable precision. The architecture does the work; the organism reaps the benefit.

We can't grow compound eyes. But we can build the cognitive architecture that gives us their advantages - if we're willing to work differently than the tools we've inherited would have us work.