hbyang
1d406f6a4e
GPT (data-driven), Claude (tactical/upset-aware), Gemini (attacking-minded) each get a distinct perspective so the 3 picks genuinely diverge instead of producing identical scorelines. Honest: still each model's own judgment. Finished matches are untouched (generation filters result_outcome IS NULL). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| ai.py | ||
| email.py | ||
| grading.py | ||
| points.py | ||
| schedule_fetch.py | ||
| schedule_sync.py | ||