Skip to main content
← Lab

ordereffect

confirmedPython · CPUModel behavior & reasoningJuly 6, 2026

the question

Will a model that says an elephant is heavier than a mouse also deny that a mouse is heavier than an elephant?

what came out

Both self-contradict on reversed comparisons (1.5B half the time, 0.5B 90%) -- and every contradiction is No-to-both: a negativity bias, not the acquiescence you'd assume. Judge-free consistency oracle.

method & receipts

  • Result: confirmed
  • 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/ordereffect