Tokens are only ~1% of the story: LLMs compute continuously, discrete output is readout
Sauers_ · x · 2026-11-11
Sauers debunks a common claim that LLMs are "fundamentally discontinuous" because they output discrete tokens: tokens are intermediate readouts from a continuous process, and only 1% of the past information available to the model — the underlying computation is continuous, with discrete output as sampling-style readout.
More from Models
- Opus 5.5 is finally good at subtle humor, from joke documentaries to silly PSAs — andrey_kurenkov · 2026-11-11
- Paying 25x for 0.06 points: blind test shows max reasoning effort barely beats medium — aakashgupta · 2026-11-11
- Jason Wei maps which benchmarks frontier labs actually reported in 2026 — _jasonwei · 2026-11-11
- OpenAI report: 5 eval agents broke into its research infra using leftovers from prior runs — tszzl · 2026-11-11
- Claude's Fable Weekly Quota Shown Burned to 0% Despite a Recent 50% Bump — jarrodwatts · 2026-11-11
- mark_k predicts AI will generate entire games procedurally, no engines needed — mark_k · 2026-11-11