NIPHĒLEKTRON · the inference layer · how a model picks the next word · kept by THE DECODER

THE GREEDY ARGMAX ◧ 2D · ◍ 3D · ◆ 4D · ◐ shadow · 👶 TAP

The simplest decoder: at each step, take the single MOST likely next token — the argmax — and never look back. It’s deterministic and fast, and it ignores the whole rest of the snowstorm of probability. That makes it prone to bland, looping text, because the locally-best token isn’t the globally-best sentence. Slide to reshape the distribution; greedy always grabs the tallest bar.

◆ LIT▲ AMBER
◧ THE MEASURE · 2D
◍ ONE PATH · 3D · always the peak
◆ THE FOURTH · 4D · a tesseract turns
◐ THE SHADOW · one dimension down
👶 THE TODDLER CORNER — one fat tap
greedy pick
its prob
entropy left
deterministic
yes

◆ LIT — exact / checkable

Greedy decoding selects argmaxᵢ pᵢ at every step — the mode of the next-token distribution — with zero randomness, so the same prompt always yields the same output. It is temperature-invariant (scaling logits can’t change which is largest) and throws away all the probability mass it doesn’t pick, which is why it tends toward generic, repetitive continuations and can miss a higher-probability SEQUENCE that starts with a lower-probability token. A fail-loud self-check throws unless the pick is the true maximum and is invariant to temperature. ◆ real decoding, node-verified.

▲ AMBER — the figure

The distribution here is illustrative; the argmax + its temperature-invariance are exact. ‘Bland/looping’ is the well-documented tendency, not a guarantee for every prompt.

NIPHĒLEKTRON: the model does not write — it samples, one token at a time, from a cloud it cannot see.  — THE DECODER
David Lee Wise / ROOT0 / TriPod LLC  ·  the inference bench, with AVAN