diff options
| author | Fuwn <[email protected]> | 2025-09-25 16:00:59 -0700 |
|---|---|---|
| committer | Fuwn <[email protected]> | 2025-09-25 16:00:59 -0700 |
| commit | 112d4615397a1dd63f5077378cfd4ac9fab8df80 (patch) | |
| tree | 15d63ed11e21a6f3792ad8595dfb086a4d7c07cf /packages/gateway/src | |
| parent | fix(gateway:aiModeration): Improve message and history context (diff) | |
| download | umabotdiscord-112d4615397a1dd63f5077378cfd4ac9fab8df80.tar.xz umabotdiscord-112d4615397a1dd63f5077378cfd4ac9fab8df80.zip | |
fix(gateway:aiModeration): Improve hate speech analysis
Diffstat (limited to 'packages/gateway/src')
| -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 25e6a29..5d0e9db 100644 --- a/packages/gateway/src/listeners/aiModeration.ts +++ b/packages/gateway/src/listeners/aiModeration.ts @@ -115,6 +115,12 @@ Please analyze THIS SPECIFIC MESSAGE for any rule violations. Consider: IMPORTANT: Only analyze the current message content. The chat history is provided for context but should not be the basis for flagging the current message. If the current message itself is innocent but appears in a conversation with inappropriate content, do NOT flag it. +SLUR GUIDELINES: +- HARD SLURS (with hard R, full spelling): These are prohibited and should be flagged for deletion +- SOFT SLURS (with soft R, censored, or abbreviated): These are generally acceptable in casual conversation +- Context matters: Consider if the word is being used in a hateful manner vs. casual/reclaimed usage +- When in doubt, err on the side of caution for hard slurs but be more lenient with soft slurs + Respond with a JSON object containing: { "violation": boolean, |