Milestone D
Each milestone is scored out of twenty under the peer-review protocol: five criteria, 0 to 4 each. Score 0 for missing evidence, 1 to 2 for an incomplete artifact, 3 for a sound artifact with limited measurement, and 4 for reproducible evidence with the measurement, its noise and its limitations stated. 14 of 20 passes. A high score never overrides a failed mastery gate.
- A pilot pitch with a dollar cost and a delivered pilot with eval numbers and failure cases.
- Three public posts with numbers, one runnable repo with the finished README, one talk.
- One upstream PR opened, following the project's contributing guide, with every line reviewed by you.
- The application kit: portfolio page, numbered resume, ten timed system-design prompts.
- A recorded mock interview in which the depth probe runs five levels deep on one project for 20 minutes without you running out.
Challenge: an interviewer asks "how did you measure hallucinations?". Answer in 60 seconds with your own numbers; your reviewer times it.
Submission checklist
For each milestone include: commit identifier; environment and setup; exact commands; the measurement, its denominator and its noise; what you expected before running; what you observed; limitations; next steps. Anything not run (a GPU run you could not afford, users you could not recruit) must say "not done", not be implied. Grade reasoning and reproducibility, not screenshots.
Use the instructor keys for module reasoning and the capstone for the final practical assessment.
Free to use: code MIT, writing CC BY 4.0, third-party media under its owners’ terms. Licence and terms.