The error-hunting game
you vs. a 63,000-parameter brain

A quantum computer's memory is guarded by an endless stream of parity checks. When checks light up, something went wrong inside — and someone has to work out what, fast, or the stored information is lost. Below: checks from a simulated honeycomb quantum memory, and a real neural network that learned to read them. It is running live in this page — no server, no tricks.

every number on this page is measured, in your browser, on the nets you're playing against

ROUND 1Get a feel for it

Errors just struck this memory — the sparks are its alarm bells. Watch them shimmer for a moment, then have a hunch: did the two stored quantum bits (A and B) make it through? No grades, no pressure — honestly, nobody can see this pattern by eye (~28% is what anyone scores), and that's exactly the point of what comes next.

Got a hunch?
YOUR HUNCHES0/0
THE NET (same sparks)0/0

A new burst loads after each reveal. Whenever you've had enough, scroll on — the net plays this game two thousand times in Round 2.

ROUND 2Now watch the net work

Same game, played fast. The net decodes each burst of sparks live in your browser; the classical gold-standard algorithm (minimum-weight matching, the one real quantum computers use today) answered the same shots ahead of time.

shot 0 / 2000
symmetry-aware neural net (live)
gold standard (matching algorithm)
lucky guessing

Honesty first: the net does not beat the gold standard here, and we don't claim it does. What's remarkable is sitting one section down.

ROUND 3The switch — why this net works at all

Here are identical twin networks: same size (63k parameters), same training examples, same everything — except one was hard-wired with the honeycomb's symmetry: "rotate the sparks 120°, and your answer must rotate the same way." The other twin had to figure the task out alone. Run them on the same 300 shots:

ordinary net

?
trained on 64,000 examples · scores 29.1% on the full 200,000-shot test — it never learned anything (guessing is 29.1%)

symmetry-aware net

?
same 64,000 examples · scores 74.7% on the full 200,000-shot test

That's the research result this page exists to show: on this code, telling the network about the lattice's symmetry isn't a speed-up — it's the difference between learning and not learning. We proved the symmetry exactly from the error model (it even swaps the roles of A and B as it rotates), then built it into the net.

ROUND 4How little data does it need?

Real machines can't hand you millions of labelled failures. Drag the slider — each stop loads the actual symmetry-aware net trained on that many examples and runs it on 300 shots, live.

trained on 250 examples
net trained on 250 examples

For scale: the ordinary twin never beats guessing even with 64,000 examples — the symmetry-aware net is already ahead of that with 250.

What you just saw, in plain terms

— Quantum computers fail constantly; an error-decoder must call every failure correctly, at speed, forever. It's a real bottleneck in the field.
— Labelled failure data from real hardware is scarce, so AI that learns from few examples is what matters — not bigger models or more compute.
— The unlock here wasn't horsepower. It was mathematics: proving the memory's exact symmetry from its error model and building that proof into the network.

training examplesordinary netsymmetry-aware netgold standard
25034.4%94.7%
1,00040.5%
4,00046.7%
16,00059.4%
64,00029.1% (≈ guessing)74.7%

Measured on 200,000 held-out shots, on the exact float16 nets shipped with this page (simulated circuit-level noise, one code size, honeycomb Floquet memory at L=6). The gold standard remains unbeaten and we claim no exception. Technical readers: the symmetry is an exact p3 space group of the detector error model with a GL(2,F₂) twist that mixes the logical qubits — solved, verified and shipped via demsym (pip install demsym); preprint in preparation.

Go deeper