Kuis Penerapan Canary dan Shadow

Jawaban dan penjelasan muncul saat Anda mengikuti kuis.

1. Apa yang mendefinisikan penerapan canary?
   • Merutekan sebagian kecil lalu lintas langsung ke versi baru sambil memantaunya
   • Mengirim semua lalu lintas ke versi baru sekaligus
   • Menjalankan versi baru hanya pada akhir pekan
   • Menyebarkan tanpa pemantauan apa pun
2. Apa karakteristik utama penerapan bayangan?
   • Tanggapannya diberikan kepada separuh pengguna
   • Ia menerima lalu lintas yang dicerminkan tetapi tanggapannya dibuang, tidak ditampilkan kepada pengguna
   • Ini hanya berjalan di lingkungan pengembangan
   • Ini segera menggantikan model produksi
3. What does a shadow deployment protect users from, and what can it still cost?
   • It uses no extra resources and cannot access user data
   • Its predictions are returned to every user
   • Candidate responses are withheld, but mirrored inference still consumes compute and needs side-effect controls
   • It guarantees the candidate has no production impact of any kind
4. How does user-facing traffic differ between a canary and a shadow?
   • Both always send candidate output to every user
   • A shadow deployment never uses production inputs
   • A canary is only an offline test
   • A canary serves candidate responses to a defined live-traffic segment; a shadow typically does not
5. What should a team define before starting a canary or shadow rollout?
   • Traffic rules, monitoring thresholds, rollout duration, and a rollback owner
   • A promise that the candidate will outperform production
   • A fixed traffic percentage that must never change
   • A requirement to expose every user to the candidate
6. Bagaimana penerapan canary dan shadow saling melengkapi?
   • Mereka adalah benda yang sama dengan nama yang berbeda
   • Shadow memvalidasi perilaku pada lalu lintas langsung tanpa risiko pengguna; canary memvalidasi dampak pengguna nyata pada sebagian kecil
   • Canary membuang tanggapan sementara bayangan memberikannya
   • Tidak ada yang melibatkan lalu lintas produksi
7. What should an operator do before mirroring production requests to a shadow model?
   • Allow the shadow model to execute writes twice
   • Assume copied requests contain no sensitive data
   • Isolate side effects and protect the handling of copied request data
   • Disable all monitoring of the candidate
8. What does a canary reveal that a shadow deployment does not directly measure?
   • Whether candidate inference consumes compute
   • How its predictions compare offline
   • Whether a model can load in the serving stack
   • How the candidate affects users who are actually served by it