01TESTED / IMPLEMENTEDLocal routing · deterministic validation · human-gated architecture

When AI Is the Wrong Tool

A local model failed an exact-normalization boundary. The correct correction was not a better prompt—it was removing inference from the lane.

When AI Is the Wrong Tool evidence diagram

The decision

Use a model where interpretation contributes value. Use ordinary software where the correct transformation is already known.

Problem

A small local model appeared promising for exact tag normalization, but its copying errors were non-monotonic. Some longer strings passed while shorter patterns failed. The independent validator already knew the correct answer, making inference an unnecessary dependency.

Intervention

The model-backed route was replaced with deterministic local computation: validate the frozen schema and sensitivity boundary, then trim, lowercase, deduplicate whole values, sort, and write a redacted audit record.

Observed result

The replacement passed the frozen representative replay, exhaustive accepted lengths, concurrency, audit, fail-closed, installed-command, and rollback checks with zero model tokens.

Verified evidence

What the record supports.

Model matrix
6 / 12
Deterministic replay
12 / 12
Accepted lengths
1–64 exact
Concurrent audit
32 / 32
Model tokens
0
  • 22/22 deterministic lane tests, twice
  • 19/19 router tests, twice
  • 7/7 eligible replay cases and 5/5 mandatory denials
  • Exact prior model-era hashes restored in rollback rehearsal

Public evidence files

Inspect the record.

Public-safe derivatives only. Source availability does not broaden the claim stated on this page.

Claim boundary

What remains unearned.

  • Not a general argument against language models
  • Not a production-ready router claim
  • No sensitive, client, or proprietary content was eligible
  • Frozen local timings are not a general benchmark

Next evidence

Keep semantic work in the separately bounded local-model extraction lane while exact transformations remain deterministic.