Study/docs
Elijah 2454ab6e95
All checks were successful
Verify and publish V2 container / build-and-push (push) Successful in 25s
Faster quiz generation: planned parallel batches, room to reason
- Output limits leave room for reasoning (answer plus 8k-64k by effort, up to
  the model maximum); a call cut off before answering is retried with double
  the limit. At "max" effort, batches were being cut off at 16k tokens.
- Quizzes are planned first (one distinct angle per question), then written
  in waves of four batches; med math runs alongside the first wave.
- Replacements for removed questions are planned and written in parallel.
- The Python check and the second review run at the same time each round.

Measured live (DeepSeek flash, max reasoning, 50 questions): 7 min 21 s with
no duplicates, against 20 min and 29 replaced duplicates without planning.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-16 11:00:27 -07:00
..
AI.md Faster quiz generation: planned parallel batches, room to reason 2026-11-16 11:00:27 -07:00
DEPLOYMENT.md Fifth revision: share-link AI safety, sturdier generation, cleaner UI 2026-11-16 09:17:50 -07:00
MIGRATION.md Harden private media and backup recovery; add V2 deployment and migration guides 2026-11-11 19:31:32 -07:00
V2-COMPARISON.md Add drag reordering, exam deadlines, frozen shared quizzes, batched OCR and semantic search 2026-11-12 11:48:20 -07:00