Files
周小舟andClaude Opus 5.5 5aa5f0fdb9 feat(pipeline): find clips in one pass over the whole transcript
Fast output no longer runs outline -> timeline -> scoring -> titles over
5000-character chunks. One call per ~60-minute window (parallel, with
overlap) reads compact id|time|text rows and returns finished clips with
rows, Chinese title, reason and score; picks are validated, deduplicated
across windows, snapped by refine_timeline and selected by select_clips, in
the legacy titled-clip shape. Short-video lengths (60-300 s, ideally
90-180 s) replace the podcast-era 90 s floor that padded answers into the
next question. Any failure falls back to the legacy steps.

MrBeast 2h06m: ~35 min / 128 calls / 500K tokens -> 38 s / 4 calls / 93K.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-01 12:53:21 +08:00
..
2025-08-26 00:18:26 +08:00
2025-08-26 00:18:26 +08:00