Skip to main content
Vansh Verma
← Lab

genentropy

null resultPython · CPUModel behavior & reasoningJuly 7, 2026

the question

Does a language model get more or less certain as it generates?

what came out

Less certain -- intrinsic next-token entropy rises over a generation, the opposite of the 'grows more committed' intuition. The smaller model is more diffuse, and the rise isn't degeneration. Python, pre-registered, code-reviewed.

method & receipts

  • Result: null result — an honest negative, reported as it came out.
  • Pre-registered — the prediction was written down and committed before the run.
  • Reproducible — one script re-runs the whole thing from scratch.
  • Independently reviewed — an adversarial review pass, kept in the repo.
  • Machine-readable claims — every reported number, in a checkable file.
  • Tested — a correctness/benchmark suite ships alongside the code.

→ read the code and re-run it

github.com/v-code01/genentropy