diff options
| author | Fuwn <[email protected]> | 2025-09-25 16:22:02 -0700 |
|---|---|---|
| committer | Fuwn <[email protected]> | 2025-09-25 16:22:02 -0700 |
| commit | e20b3728553476c4a971b336923084fa5ceb9a95 (patch) | |
| tree | cf7d85623af06749a74f7a4838e1f0ed1d118dff /packages | |
| parent | fix(gateway:aiModeration): Improve adult content analysis (diff) | |
| download | umabotdiscord-e20b3728553476c4a971b336923084fa5ceb9a95.tar.xz umabotdiscord-e20b3728553476c4a971b336923084fa5ceb9a95.zip | |
fix(gateway:aiModeration): Improve adult content analysis
Diffstat (limited to 'packages')
| -rw-r--r-- | packages/gateway/src/listeners/aiModeration.ts | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/packages/gateway/src/listeners/aiModeration.ts b/packages/gateway/src/listeners/aiModeration.ts index b8265b9..17b396f 100644 --- a/packages/gateway/src/listeners/aiModeration.ts +++ b/packages/gateway/src/listeners/aiModeration.ts @@ -147,6 +147,13 @@ Respond with a JSON object containing: If no violation is found, set "violation" to false and provide a brief explanation of why the message is acceptable. CRITICAL: Only analyze the content in quotes above (the current message). Ignore all content in the chat history section. If the current message is innocent (like "true", "yes", "no", etc.) but appears after inappropriate content in the chat history, do NOT flag it. + +CONTEXT UNDERSTANDING: +- Read sentences carefully and understand their actual meaning +- "pregnant with my daughter" means the baby will be the speaker's daughter, NOT that the daughter is pregnant +- "pregnant with my son" means the baby will be the speaker's son, NOT that the son is pregnant +- Do not misinterpret family relationships or pregnancy announcements +- Only flag if there is genuinely inappropriate content, not innocent family/pregnancy references `; const response = await fetch("https://api.openai.com/v1/chat/completions", { method: "POST", |