Your brain solves crosswords the way future AI will think

You don't solve puzzles in a straight line

Think about how you actually do a crossword. Maybe you start with 3-across because you know the answer. That gives you the second letter of 1-down and the fourth letter of 5-down. Now you have fragments. Pieces. And from those pieces, your brain starts filling in possibilities in every direction at once.

It's the same with word searches. Nobody scans letter by letter, left to right, top to bottom. You let your eyes wander, and your brain detects patterns — a familiar sequence of letters, a word forming diagonally, a cluster that doesn't look random. You process the entire grid at once, not sequentially.

The brain as a pattern-completion machine

What you do when solving puzzles is something neuroscientists have studied for decades. The brain doesn't wait for all the information to arrive before drawing conclusions. It takes the available fragments and fills in the rest based on context, memory, and probability.

You do this all day long without noticing. You read a sentence with a missing word and your brain completes it before you notice the gap. You walk into a dark room and "see" furniture you can barely make out, because your brain fills in the shapes from memory. You hear half a word in a noisy bar and understand the entire sentence.

This is the brain's default mode: take partial information, fill in the gaps, in any direction, all at once.

What Ilya Sutskever noticed

Ilya Sutskever is one of the most important people in AI. He co-founded OpenAI, left in 2024, and created a new company called Safe Superintelligence Inc. (SSI), focused on building the next generation of artificial intelligence. Recently, he described something that looks a lot like what happens when you solve a crossword.

In his words (paraphrased): the cerebral cortex works like a pattern-prediction machine. If you provide only part of the information, any region of the cortex can deduce what's missing. If you lock some variables into a specific state — treating them as reality in that moment — the brain can calculate, predict, and fill in the rest of the picture in any direction. Not just left to right. Not just forward. In all directions at once. He calls this omnidirectional inference.

The crossword as a model of thought

Back to the crossword. When you fill in 3-across and gain a letter in 5-down, what happened? You locked a variable (the letter) into a specific state (the letter you wrote). Now 5-down has a constraint it didn't have before. Your brain uses that constraint to narrow down the possibilities. Maybe 5-down starts with "M" and has 6 letters. That alone is enough for your brain to start generating candidates.

This is exactly what Ilya is describing. You "lock" some known values — the letters you've already filled in — and your brain infers the rest. It doesn't go clue by clue in order. It works from whatever information is available, in whichever direction helps the most.

Word searches work the same way, but in reverse. Instead of having clues and looking for letters, you have letters and look for words. Your brain scans the grid with no fixed path, recognizing word fragments in all eight directions. You see "CR" and check whether "CROSSWORD" continues diagonally. If it doesn't, you give up instantly. The brain evaluates and discards possibilities at a speed no sequential system can match.

Why current AI doesn't work this way

Current AI models like ChatGPT and Claude work in one direction only. They receive a sequence of words and predict the next one. Always forward, always one token at a time. It's like trying to solve a crossword by reading each clue in order, from 1-across to the last down, filling in each answer before looking at the next clue. Nobody solves crosswords that way, because it's painfully slow and ignores all the information you could get from the crossings.

The brain does it differently. When you walk into a room, you don't process the scene pixel by pixel. You take in the entire space at once. You notice the table, the chair, the window, and fill in details you can barely see based on what you expect to be there. It's a crossword where you already have half the letters and your brain completes the other half from experience.

Puzzles as a preview of future AI

What Ilya proposes is that the next generation of AI should work more like you solving a crossword and less like a typewriter spitting out one letter at a time. A system that can "lock" some known facts and fill in everything else from any direction at once.

Imagine an AI that works like your brain on a word search: it absorbs the entire grid (the problem), detects patterns from multiple angles, and arrives at answers without going through everything step by step. That's omnidirectional inference.

You already do this

The interesting part is that you don't need to understand neuroscience or AI architecture to know what Ilya is talking about. You already experience omnidirectional inference every time you pick up a puzzle. You lock what you know, your brain radiates outward from those anchor points, and fills in the rest without following a fixed sequence.

Next time you solve a crossword or scan a word search, pay attention to how your brain works. It doesn't go in order. It doesn't follow a script. It jumps, guesses, confirms, backtracks, and fills in gaps in every direction. According to one of the most important AI researchers in the world, that messy, non-linear process is what the future of artificial intelligence looks like.