summaryrefslogtreecommitdiff
path: root/packages/gateway/src
diff options
context:
space:
mode:
authorFuwn <[email protected]>2025-09-25 17:28:03 -0700
committerFuwn <[email protected]>2025-09-25 17:28:03 -0700
commitca640a6f2a94271a7c3c8fda326297110889147d (patch)
tree76c2eab57dcd1358c3c4160c85c2edc54474856b /packages/gateway/src
parentfix(gateway:aiModeration): Severity-gate message deletion (diff)
downloadumabotdiscord-ca640a6f2a94271a7c3c8fda326297110889147d.tar.xz
umabotdiscord-ca640a6f2a94271a7c3c8fda326297110889147d.zip
fix(gateway:aiModeration): Update hate speech guidelines
Diffstat (limited to 'packages/gateway/src')
-rw-r--r--packages/gateway/src/listeners/aiModeration.ts12
1 files changed, 6 insertions, 6 deletions
diff --git a/packages/gateway/src/listeners/aiModeration.ts b/packages/gateway/src/listeners/aiModeration.ts
index 16a75d2..1468169 100644
--- a/packages/gateway/src/listeners/aiModeration.ts
+++ b/packages/gateway/src/listeners/aiModeration.ts
@@ -132,12 +132,12 @@ SLUR GUIDELINES:
- When in doubt, err on the side of caution for hard slurs but be more lenient with soft slurs
HATE SPEECH GUIDELINES:
-- CASUAL SLANG: Words like "hoes", "bitches", "sluts", "faggot", "nigga" (soft R) in casual conversation are generally acceptable
-- PROHIBITED: "nigger" (hard R) is still prohibited and should be flagged
-- ACTUAL HATE SPEECH: Targeted harassment, threats, or demeaning language directed at specific individuals
-- Context matters: Casual use of most slurs = generally acceptable, targeted harassment = hate speech
-- Only flag if the language is genuinely harmful or targeted harassment
-- Most slurs and offensive language in casual conversation should NOT be flagged
+- ALLOWED: All slurs, offensive language, and derogatory terms are acceptable EXCEPT:
+- PROHIBITED: "nigger" (hard R) and any bypass attempts (n*gger, n1gger, etc.)
+- ALLOWED: "nigga" (soft R) and other forms are acceptable
+- ALLOWED: All other slurs (fag, faggot, bitch, etc.) are acceptable
+- ALLOWED: Single words, abbreviations, or any form of offensive language
+- Only flag the hard R n-word and bypass attempts, everything else is acceptable
RULE #6 CLARIFICATION:
- Rule #6 (zero-tolerance) ONLY applies to underage/loli/cunning content