JesseMarkowitzandClaude Opus 5
fa3769d0fe
Research toward building a content pack from a story corpus, kept on its own branch and independent of the game. Records the selection experiments against blind labels, and settles selection as gate G2 followed by a human review: review.py writes REVIEW.md and a review.json form, apply_review.py checks the filled form and writes situations.json for the next stage. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01C6UDQ9o6L6Ey173U7XVou6
7 lines
224 B
Plaintext
7 lines
224 B
Plaintext
40 scenes, resuming at 0, model qwen2.5:3b-instruct
|
|
10/40 18s prefill 2s gen 6s
|
|
20/40 35s prefill 4s gen 12s
|
|
30/40 55s prefill 7s gen 19s
|
|
40/40 74s prefill 9s gen 25s
|
|
done: 40 summaries, 74s this session
|