MythEclipseandClaude Opus 4.8 da885339f9 fix(ai-moderation): remove user history from prompt to eliminate confirmation bias loop ...

user_history (riwayat flag sebelumnya) dan clean_streak/total_infractions
dikirim ke LLM setiap kali menganalisis pesan — ini bikin self-fulfilling
prophecy: user yg pernah kena false positive jadi makin gampang dituduh
lagi, dan link Instagram pun dianggap sexual_deviation cuma karena
riwayat user.

Changes:
- Hapus getUserRecentInfractions dari text batch path
- Hapus getUserRecentInfractions dari media analysis path
- Hapus import getUserRecentInfractions yg gak dipakai
- Ubah instruksi prompt dari 'jadilah lebih tegas jika riwayat jelek'
  jadi 'setiap pesan dinilai berdasarkan isinya sendiri'

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-06-06 13:55:24 +07:00

..

backend

fix(concurrency): eliminate all identified double-queue and race conditions

2026-06-05 16:09:23 +07:00

discord-gateway

fix(ai-moderation): remove user history from prompt to eliminate confirmation bias loop

2026-06-06 13:55:24 +07:00

frontend

fix(concurrency): eliminate all identified double-queue and race conditions

2026-06-05 16:09:23 +07:00