diff options
| author | Fuwn <[email protected]> | 2025-09-25 17:21:04 -0700 |
|---|---|---|
| committer | Fuwn <[email protected]> | 2025-09-25 17:21:04 -0700 |
| commit | c0b346019cb0253c582c94dcd1455e646bd1bb53 (patch) | |
| tree | f031bf409724419467f8f898176c4ef61edd4293 | |
| parent | fix(gateway:aiModeration): Improve hate speech analysis (diff) | |
| download | umabotdiscord-c0b346019cb0253c582c94dcd1455e646bd1bb53.tar.xz umabotdiscord-c0b346019cb0253c582c94dcd1455e646bd1bb53.zip | |
fix(gateway:aiModeration): Improve joke analysis
| -rw-r--r-- | packages/gateway/src/listeners/aiModeration.ts | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/packages/gateway/src/listeners/aiModeration.ts b/packages/gateway/src/listeners/aiModeration.ts index 57bf4c7..0764307 100644 --- a/packages/gateway/src/listeners/aiModeration.ts +++ b/packages/gateway/src/listeners/aiModeration.ts @@ -98,6 +98,12 @@ You are an AI moderator for a Discord server. Analyze the following message for CRITICAL INSTRUCTION: DO NOT flag messages for Rule #6 (underage content) based solely on family relationship words like "mom", "dad", "daughter", "son", "sister", "brother". These words do NOT automatically indicate underage content. Adults can roleplay family scenarios. Only flag Rule #6 if there is explicit indication of actual minors (age mentions, school settings, etc.). +JOKE RECOGNITION: Recognize obvious jokes, sarcasm, and humorous statements. Do not flag: +- Obvious jokes like "No more males in the near future" (clearly humorous) +- Sarcastic statements like "Just send a nuke to our location" (obviously not serious) +- Casual service offers like "I got contacts" (not serious self-promotion) +- Use common sense to distinguish between genuine violations and humour + SERVER RULES: ${SERVER_RULES} |