From e0cdde79a1b9ecf74aae54bbe18d7eebfd66cc54 Mon Sep 17 00:00:00 2001 From: Paillat Date: Sat, 11 Nov 2023 18:16:39 +0100 Subject: [PATCH 1/2] Fix typo in AI-MODERATION.md Signed-off-by: Paillat --- detailed_guides/AI-MODERATION.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/detailed_guides/AI-MODERATION.md b/detailed_guides/AI-MODERATION.md index 1f9f507b..0a22c5f4 100644 --- a/detailed_guides/AI-MODERATION.md +++ b/detailed_guides/AI-MODERATION.md @@ -4,7 +4,7 @@ `/mod set status:off` - Turn off automatic chat moderations -`/mod set status:off alert_channel_id:` - Turn on moderations and set the alert channel to the channel ID you specify in the command. +`/mod set status:on alert_channel_id:` - Turn on moderations and set the alert channel to the channel ID you specify in the command. `/mod config type: hate:# hate_threatening:# self_harm:# sexual:# sexual_minors:# violence:# violence_graphic:#` - Set the moderation thresholds of the bot for the specific type of moderation (`warn` or `delete`). You can view the thresholds by typing just `/mod config type:` without any other parameters. You don't have to set all of them, you can just set one or two items if you want. For example, to set the hate threshold for warns, you can type `/mod config type:warn hate:0.2` @@ -25,4 +25,4 @@ To set a certain role immune to moderations, add the line `CHAT_BYPASS_ROLES="Ro If you want to have the bot pre-moderate things sent to commands like /gpt ask, /gpt edit, /dalle draw, etc, you can set `PRE_MODERATE="True"` in the `.env` file. **The above server is NOT for support or discussions about GPT3Discord** - \ No newline at end of file + From 3d6f94a307c9be282bf6330ca4e83b2425192397 Mon Sep 17 00:00:00 2001 From: Paillat Date: Sat, 11 Nov 2023 20:18:23 +0100 Subject: [PATCH 2/2] Remove broken invite to test server in AI-MODERATION.md Signed-off-by: Paillat --- detailed_guides/AI-MODERATION.md | 2 -- 1 file changed, 2 deletions(-) diff --git a/detailed_guides/AI-MODERATION.md b/detailed_guides/AI-MODERATION.md index 0a22c5f4..3768f10d 100644 --- a/detailed_guides/AI-MODERATION.md +++ b/detailed_guides/AI-MODERATION.md @@ -18,8 +18,6 @@ The bot uses numerical thresholds to determine whether a message is toxic or not There are two thresholds for the bot, there are instances in which the bot will outright delete a message and an instance where the bot will send a message to the alert channel notifying admins and giving them quick options to delete and timeout the user (check out the screenshots at the beginning of the README to see this). -If you'd like to help us test and fine tune our thresholds for the moderation service, please join this test server: https://discord.gg/CWhsSgNdrP. You can let off some steam in a controlled environment ;) - To set a certain role immune to moderations, add the line `CHAT_BYPASS_ROLES="Role1,Role2,etc"` to your `.env file. If you want to have the bot pre-moderate things sent to commands like /gpt ask, /gpt edit, /dalle draw, etc, you can set `PRE_MODERATE="True"` in the `.env` file.