CL-08 / Translation / proposed
Translation with a visible review step
Where do short community notices lose meaning during translation?
01 / One week
Make the smallest useful proof.
Write 20 invented notices; compare draft translations with qualified human review for names, dates, instructions and ambiguity.
02 / Four weeks
Stretch the experiment.
Add a glossary, side-by-side editor and disagreement log for two reviewed languages.
03 / Materials
Start with what is available.
- $0–40 materials; human review must be separately budgeted
- Skills to practise: Language skills, content design, evaluation
Illustrative materials only. Equipment purchases, expenses and access need human review.
04 / Privacy + boundaries
Choose a safe test fixture.
No sensitive notices, medical/legal advice or real personal data. Do not label machine output as human-verified.
05 / Success
Measure the change.
All names, dates and instructions match after human review; uncertainty remains visible
06 / Deliverable + review
Leave a usable handoff.
Reviewable prototype, glossary and error taxonomy
Human review: A qualified human reviewer is required for each language. Mike approves any public translation; agents only draft.
Before work enters the world.
- Pay, hours, eligibility, supervisor, location, agreements and legal review must be resolved before recruitment or work begins. Budgets are illustrative materials estimates in USD, exclude labor, tax and shipping, and are not spending authorization.
- Use synthetic or licensed public fixtures first. A human supervisor must approve any participant involvement, consent, collection and data lifecycle.
- Agents may draft, code, propose tests and document evidence. They cannot supervise interns, approve their own work or infer authority to send messages, buy materials or publish.
- PointCast publication is the programme’s intended context. Physical venues, partners and installations need separate confirmation; no external venue partnership is claimed.
- Credit every contributor with permission. Publish measured results and limitations only after human review; preserve a record of corrections.