A plain-language explainer — same story, real giant-scale numbers
The Whole Story walked our tiny AI from a folder of old plays to one sentence. Here's the same six-stage story, side by side with a real reasoning model built the way you asked — a cluster of datacenter GPUs, trillions of words. Same shape. Vastly bigger numbers.
Our tiny AI
1.06 MBone file of Shakespeare, 40,000 linesDeepSeek-V3 (2024)
14.8 trilliontokens of training text — roughly tens of terabytesSource: DeepSeek-V3 Technical ReportSame idea, wildly different amount of reading. If our file were a single page, a training run like DeepSeek-V3's would be a pile of pages several times taller than Mount Everest.
Our tiny AI
10,788,929numbers, nudged 5,000 times, on 1 gaming GPU, in about 17 minutesDeepSeek-V3
671 billionnumbers (37 billion used per word — more on that below), nudged across 2,048 datacenter GPUsSource: DeepSeek-V3 Technical ReportThat's roughly 62,000 times more numbers than our AI has, being nudged on 2,048 times more GPUs at once — and each of those GPUs is itself far more powerful than ours. DeepSeek reports the whole run took 2.788 million GPU-hours. Spread across their 2,048 GPUs, that works out to about 57 days of the entire cluster running nonstop — and cost about $5.6 million in compute, by their own estimate.
Meta's Llama 3.1 405B is the one that really did use H100s: 16,000+ H100 GPUs, 15+ trillion tokens, about 30.84 million GPU-hours total — roughly 80 days across that whole cluster.Source: Meta, "Introducing Llama 3.1"
Same idea as our AI: real models like this turn your words into numbers using a fixed lookup table, built the same way ours was — by scanning huge amounts of text and cataloging the pieces that show up. Theirs just has a lot more entries than our 65, and the pieces are usually chunks of words, not single letters.
Our tiny AI
384 numbersper position, per layer — 6 layers deepDeepSeek-V3
7,168 numbersper position, per layer — 61 layers deepSource: DeepSeek-V3 Technical ReportSame problem as before — nobody has a dictionary for any of these numbers either — just about 18 times as many numbers, spread across 10 times as many layers.
Same shape as our tiny AI's last step: all that mystery math eventually gets squeezed back down into one number for every entry in the dictionary — a real, readable list of odds for what word or word-piece comes next. That list has a key again, for the same reason ours did: it was built to line up with the dictionary from step three, on purpose.
One piece of text out, the same weighted-lottery way ours works — just with a genuinely staggering number of possible next pieces to choose from, and a genuinely staggering number of unlabeled numbers deciding the odds. Then, exactly like ours, it happens again for the next piece. And again.
No — and that's the actual point of this page. Every real number above came from a company with essentially unlimited resources to solve this if solving it were just a matter of scale or budget. They didn't write a dictionary for the 7,168 numbers either. It's not on their roadmap because nobody knows how, not because nobody can afford it.
Bigger machine, same missing dictionary — just 18 times more numbers per layer, spread across 10 times more layers, with a routing step on top that we can watch but not explain. Scale made the guessing machine much better at guessing. It didn't make the guessing machine legible.