[rasengan]

That's pretty awesome. I wanted to try an experiment like that with ChatGPT moderating an IRC channel. I started here https://github.com/realrasengan/chatgpt-groupchat-test determining whether it was being spoken to and whether it should respond or not, and then providing that in json form so that it could be asked then to create the response in a sort of mini-chain of responses. It could also simply be asked, 'do you think this person should be kicked for their actions?' (Just for experiment and science purposes of course lol).

[Taxz]

Quin69 on twitch has gpt-4 hooked up to do exactly this. It reviews a users logs, gives a sentiment analysis and then times them out based on how rude they are. I believe it can also just read the chat logs on a regular basis and time out the worst offender every x minutes.

Here's a clip: https://clips.twitch.tv/BreakableFriendlyCookieTakeNRG-EUXd5...

[visarga]

Probably the only way to ensure civil forums in the future when nobody can be bothered to moderate by hand.

[tanseydavid]

>> the only way to ensure civil forums

GPT will likely come to the conclusion that the only way to ensure civil forums is to keep the humans out entirely.

[unixhero]

Irc? Then you're halfway there to command a botnet