Domain-blind sentence
- Id
- domain-blind-sentence
- Status
- Active
- Severity
- high
- Detection
- judge
- Evidence grade
- corroborated
- Languages
- en
- Added
- 2026-08-15
- Updated
- 2026-08-15
Currently signals low-effort writing.
What it is
A sentence that parses, scans and means nothing workable. Anyone who has done the thing once reads it and stops. The failure is not in the grammar and not in the facts as stated. It is that the steps cannot be carried out in the order given.
Why it reads as machine-made
Generated text is fluent about a subject without having done it, and practice is where the ordering constraints live. The tell surfaced publicly through a set of sports and finance explainers published under fabricated bylines in 2023, where the giveaway was a piece of advice about a sport that assumed equipment the sport requires. A single such sentence tells you nobody with the relevant experience read the draft, which is a fact about the publishing process and a useful one.
Specimens
Sourdough is a good first bread for beginners, because the starter can be mixed the same morning you plan to bake and needs no special handling.
Sourdough is a hard first bread, because the starter takes about a week to become reliable. Start it on a Monday, feed it every day, and expect the first loaf that rises properly around the second weekend. Ours took eleven days and two failures before it worked.
Nothing in the first version is ungrammatical or self-contradictory. It is wrong about an ordering constraint that only shows up in practice.
Hold the sprint retrospective before the sprint begins, so the team knows in advance what went wrong and can plan around it.
Hold the retrospective in the last hour of the sprint, while people still remember Tuesday. We tried moving it to the following Monday and the notes got vaguer every time, so we moved it back.
The first version inverts an ordering the practice depends on. It reads fine and cannot be done.
How it is detected
- Rubric
- Task: decide whether the instructions could be carried out by someone doing this work. Step 1. Extract every imperative, recipe step, causal claim and piece of advice. Step 2. Test each against these failure classes: (a) ordering, where a step requires the output of a step that comes later; (b) prerequisite, where a required material, tool, permission or condition is never obtained; (c) magnitude, where a stated time, quantity or cost is off by an order of magnitude against ordinary practice; (d) category, where a procedure is applied to a material or system it does not apply to; (e) safety, where following the instruction would injure someone or destroy the thing being worked on. Step 3. For each hit, write the one sentence a practitioner would say in reply. Escape hatches: deliberate novelty, where the text argues for the unusual method and gives a reason; regional or historical practice that differs from the reviewer's; specialist equipment that changes the constraint; text marked as untested, speculative or fictional; a reviewer with no knowledge of the domain, who should return UNKNOWN rather than guess. Decision. FLAG on one hit in classes (a), (b) or (e), which are hard failures. Two or more hits in (c) or (d) also FLAG. Otherwise PASS. Output: the sentence, the failure class, the practitioner's reply, and the verdict.
Who writes this way legitimately
Freelancers write outside their expertise for a living, and a competent generalist on an unfamiliar beat produces exactly this sentence without any tool involved. Domains also disagree with themselves: bakers, mechanics and clinicians all hold live arguments about ordering that a reviewer from one school will read as an error from another, and regional practice differs enough that an instruction absurd in one country is standard in the next. Translation strips the qualifiers that made a step conditional. The fix in every case is a subject-matter read, which is cheaper than an argument about authorship and produces a better piece either way. A reviewer without the domain should say so rather than score it.
Model attribution
No vendor can be named. The published cases used an unnamed in-house generator. No study measures practical absurdity per vendor, and the failure is about missing practice rather than about a model family.
Status history
| Date | Status | Rationale |
|---|---|---|
| 2026-08-15 | Active | The 2023 fake-byline investigation and its trade-press follow-up both identify the impossible instruction as the sentence that broke the story. The pattern survives model improvement because it comes from having no practice rather than from weak language. |
Sources
- 01Futurism, Sports Illustrated published articles by fake AI-generated writerspressaccessed 2026-08-14
- 02Poynter, Sports Illustrated and the AI byline problempressaccessed 2026-08-14
CC BY 4.0 / The AI Tells Index, feedsquad.com/ai-tells